Skip to content
IAM Insights

Explainers · Glossary

OAuth

OAuth 2.0 · OAuth 2.1 · RFC 6749

By Boston Identity · Explained · 7 min read

The short answer

OAuth is an IETF standard that lets an application get limited access to a web service, either for a person who approves it or on its own behalf. The application uses an access token, separate from the person's credentials.

What it is
A standard
Defined by
IETF, RFC 6749 (2012)
Who it's for
Anyone approving apps or agents that reach company data
In our briefings
343By month of the source: 2025-12: 5, 2026-01: 8, 2026-02: 19, 2026-03: 18, 2026-04: 16, 2026-05: 15, 2026-06: 18, 2026-07: 26, 2026-08: 8, 2026-09: 46, 2026-10: 50, 2026-11: 44by month, last 12
01

What is OAuth?

OAuth 2.0 is a framework the Internet Engineering Task Force (IETF) published in 2012 as RFC 6749, a Standards Track document.S1 It lets a third-party application get limited access to a web service, either for a person who approves it or on its own behalf.S1

Before OAuth, a person who wanted a printing service to reach their photos had to give it their password. The printing service then stored that password and gained access to everything behind it. The only way to cut it off was to change the password, which cut off every other app as well.§1 OAuth gives the application its own credential instead: an access token, a string that stands for a specific scope, lifetime and other access attributes.§1 An authorization server issues the token with the person's approval, and the application presents it to the service that holds the data.§1

The standard names four roles.§1.1 The resource owner can grant access; when it is a person, the RFC calls them the end-user. The resource server hosts the protected data. The client is the application asking for access. The authorization server issues tokens after it authenticates the resource owner and gets their approval. A single authorization server may issue tokens that many resource servers accept.§1.1

OAuth decides what an application may reach, not who the user is. Asked what they build today, one integrator named OpenID Connect for sign-in and OAuth for authorization,2 and RFC 6749 itself warns that a sign-in built on its implicit grant needs extra checks.3

02

How does OAuth work?

The RFC defines four ways to get a token, called grants, and prefers the one where the authorization server stands between the client and the person.§1.2 In that authorization code grant, the person's web browser carries messages between the client app and the authorization server, and a resource server holds the data. A client acting for itself can instead use the client credentials grant, where it gets a token with its own credentials alone.§1.3.4

Figure steps
  1. The client sends the person to the authorization server
  2. The authorization server signs the person in and asks
  3. The authorization server sends back a code
  4. The client trades the code at the token endpoint
  5. The authorization server checks and issues tokens
  6. The client calls the resource server with the token
Fig. 1

The person signs in only at the authorization server, so the client app ends up holding a short-lived code and then a token, never the person's password.

Drawn from RFC 6749, section 4.1

Swipe for the full figure →

  1. The client sends the person to the authorization server

    The client redirects the person's browser to the authorization server's authorization endpoint. The request carries the client's identifier, the scope it wants, a state value the client keeps, and a redirection URI, the address the server will send the browser back to.§4.1 The RFC says the state value should be used to prevent cross-site request forgery.§4.1.1

  2. The authorization server signs the person in and asks

    The authorization server authenticates the person through the browser and learns whether they grant or deny the client's request.§4.1 Because the person signs in only at the authorization server, their credentials are never shared with the client.§1.3.1

  3. The authorization server sends back a code

    If the person agrees, the authorization server redirects the browser to the client's redirection URI with an authorization code and the client's state value.§4.1 The code must expire shortly after it is issued, and the RFC recommends a lifetime of no more than 10 minutes.§4.1.2 The code is bound to the client identifier and the redirection URI.§4.1.2

  4. The client trades the code at the token endpoint

    The client sends the code to the authorization server's token endpoint, along with the redirection URI it used before.§4.1 The server must require client authentication from a confidential client, one able to keep its credentials secret.§2.1,§4.1.3 The client must not use a code more than once.§4.1.2

  5. The authorization server checks and issues tokens

    The authorization server checks that the code is valid, that it was issued to this client, and that the redirection URI matches.§4.1.3 If all holds, it returns an access token and, optionally, a refresh token, which the client can later present to get a new access token when the current one expires.§1.5 If a code is used twice, the server must deny the request and should revoke the tokens already issued from it.§4.1.2

  6. The client calls the resource server with the token

    The client asks the resource server for the protected data and presents the access token.§1.2 The resource server validates the token and, if it is valid, serves the request.§1.2 The RFC leaves out of scope how the authorization server and resource server talk to each other,§1.1 and how the resource server validates a token.4

03

Why does OAuth matter now?

A panel of identity practitioners calls the Model Context Protocol (MCP), with its OAuth layer, the de facto protocol for AI agents' tool calls.5 As of its 28 July 2026 revision, an MCP client is an OAuth 2.1 client and an MCP server is an OAuth 2.1 resource server.6 Authorization in MCP is optional, and nothing in the token says which person the agent is acting for.6 Two identity product builders told one show that vendors under pressure wrap the API they already have, so the fine-grained scopes an agent needs were never there to expose.7

Stolen tokens are already in the incident record. In the public account of the April 2026 Vercel breach, an infostealer at the AI vendor Context.ai exposed OAuth tokens it stored, and those opened a Vercel employee's Google account.8 Consent can be phished as well. Datadog Security Labs demonstrated a Copilot Studio agent that sends a victim to the consent screen of an attacker's app and forwards the token once the victim approves; Microsoft treats it as social engineering rather than a vulnerability.9

OAuth is also moving into written requirements for agents. OWASP's AI security verification standard, AISVS 1.0, has MCP servers validate the access token on every request under OAuth 2.1 and never pass a client's token on to downstream APIs.10 OAuth 2.1 is still a draft that drops the implicit and password grants.3 Dick Hardt, who says he is working on it, says it adds no new features and does not make proof of possession required.11

04

Where does it fit?

Compared withHow OAuth differs
JWTA JSON Web Token (JWT) is a token format, not a way to get a token. RFC 6749 lets an access token be an identifier or a signed string that carries the authorization itself,§1.4 and a common JWT format for access tokens came later, in RFC 9068.4
Proof of possessionProof of possession makes the client prove it holds a key when it uses a token. RFC 6749 has no such check; the standards that add it, mutual TLS in RFC 8705 and DPoP in RFC 9449, are separate and optional.12
Model Context ProtocolThe Model Context Protocol connects AI assistants to tools and reuses OAuth for authorization: its client is an OAuth 2.1 client and its server an OAuth 2.1 resource server.6
OAuth Identity and Authorization Chaining Across DomainsRFC 6749's delegation is one hop, from a resource owner to one client.13 Carrying authorization further relies on extension grants such as token exchange (RFC 8693), which plug into the hook RFC 6749 left for new grant types.13
05

What goes wrong?

  • A bearer token, the kind RFC 6750 defines, works for whoever holds it.1 RFC 6749 gives a resource server no way to check that the client presenting a token is the client it was issued to.12 RFC 9700, published in 2025, says servers should bind access tokens to a key the client holds, a should rather than a must.12
  • Two of the four grants carry warnings. The implicit grant hands the access token over in the browser redirect without authenticating the client.§1.3.2 The RFC says the password grant keeps the password anti-pattern OAuth set out to avoid, and RFC 9700 now says it must not be used.3
  • Many protections in the 2012 text are only recommendations. Transport Layer Security (TLS) on the redirection endpoint is a should, because requiring it then was a significant hurdle for many developers.§3.1.2.1 RFC 6749 requires simple string comparison of redirect URIs only when the full URI was registered, and mentions refresh token rotation only as an example.14 RFC 9700 later required exact redirect matching, and rotated or key-bound refresh tokens for public clients.14
  • A public client, such as an app running in a browser or on a phone, cannot keep a secret.§2.1 For such a client, the server checks the code only against a client identifier that the RFC says is not a secret.14
  • People often approve what they cannot judge. RFC 6819 makes the end user part of the security model while conceding that users often cannot judge what they approve, and it offers no fix for malicious apps a user installs.15
  • Interoperability is not built in. The RFC warns it is likely to produce a wide range of non-interoperable implementations, and it leaves client registration and endpoint discovery partially or fully undefined.§1.8
06

What should a security leader ask?

  1. 01

    Which third-party apps and AI agents hold OAuth tokens to our core systems today, and with what scopes?

  2. 02

    Are our access tokens bearer tokens, or bound to a key the client must prove it holds?

  3. 03

    Which scopes can an ordinary employee grant to an app without an administrator's approval?

  4. 04

    Do any of our applications still use the implicit or password grant?

  5. 05

    How long do our refresh tokens last, and can we revoke one app's tokens without touching the others?

07

Sources

›Evidence: 15 claims from 11 briefings
  1. 1BI-FIND-2012-0001 · RFC 6750 tokens work for whoever holds them; RFC 9700 now urges key binding and bars them from query stringsRFC 6750 defines a bearer token as one that any party holding it can use, with no need to prove possession of a cryptographic key, and the RFC specifies no way to tie a token to its holder. We read its security advice as one long effort to stop leaks and limit the damage when they happen. Jones and Hardt call keeping tokens from unintended parties "the primary security consideration". Clients MUST use TLS and validate the resource server's certificate chain, tokens MUST NOT be stored in cookies sent in the clear, and token lifetimes MUST be limited. Token servers SHOULD issue tokens that last one hour or less and carry an audience restriction. RFC 9700, which updates it, adds key binding: authorization and resource servers SHOULD sender-constrain access tokens, binding each to a key the client holds through mutual TLS (RFC 8705) or DPoP (RFC 9449).
  2. 2BI-FIND-2026-0484 · An integrator builds agent access on OpenID Connect and OAuth; clients want one view across many MCP gatewaysAsked what they build today when a client wants people and embedded third-party agents in the same system, Zitel said it was "sticking to the basics": OpenID Connect for sign-in and OAuth for authorization, with delegated scopes, de-scoping and on-behalf-of flows ("that's what we're actually building"). Bonifield described what he sees inside clients: MCP gateways multiplying, from data platforms such as Databricks and proxies such as LiteLLM, and clients asking whether the real single sign-on is "a gateway of gateways"; he would start with visibility across the gateways and identity providers and consolidate later. No client is named.
  3. 3BI-FIND-2012-0005 · RFC 6749 admits a server can't tell who presents a token; the fixes arrived in 2020 and 2023Two of the four grants RFC 6749 defines come with warnings in its own security section. The implicit grant returns the access token in the redirect with no client authentication (§4.2), and §10.16 says any sign-in protocol built on OAuth must not use it without extra checks, such as audience-restricting the token. Of the password grant, §10.7 says it "carries a higher risk than other grant types because it maintains the password anti-pattern this protocol seeks to avoid," and asks servers and clients to minimize its use. Thirteen years on, in the later documents we have read, RFC 9700 says the password grant MUST NOT be used and clients SHOULD NOT use the implicit grant, and the OAuth 2.1 draft leaves both out.
  4. 4BI-FIND-2012-0007 · RFC 6749 admits a server can't tell who presents a token; the fixes arrived in 2020 and 2023RFC 6749 warns that on its own it "is likely to produce a wide range of non-interoperable implementations" (§1.8). It names client registration, authorization server capabilities and endpoint discovery as examples of required pieces it leaves undefined, and it puts how a resource server validates a token (§7) and how the authorization and resource servers talk to each other (§1.1) out of scope. Among the RFCs we have read, later standards filled several of these gaps: dynamic client registration in RFC 7591 (2015), server metadata for capabilities and discovery in RFC 8414 (2018), and a common JWT format for access tokens in RFC 9068 (2021).
  5. 5BI-FIND-2026-0069 · The rules cover one agent acting for one person; they break when that agent hands work to other agentsMCP with its community-added OAuth layer is the de facto tool-call protocol, and the panel is unanimous that it is not a policy system: it says how a client gets a token, not who is allowed to do what. The access decision is being pulled up into identity providers and agent gateways that sit above the protocol, which is exactly where Okta, Microsoft Entra and Ping Identity already sit for humans.
  6. 6BI-FIND-2026-0189 · MCP's authorization spec makes the agent a plain OAuth client and leaves delegation to an extensionAs of the 28 July 2026 revision, an MCP client is an OAuth 2.1 client and an MCP server is an OAuth 2.1 resource server, and that is the whole identity model. Authorization is optional; HTTP transports SHOULD use it, and 'implementations using an STDIO transport SHOULD NOT follow this specification, and instead retrieve credentials from the environment'. The authorization server is out of scope. There is no actor claim, no on-behalf-of flow, no token exchange and no transaction-token profile: nothing in the token says whom the agent is acting for, which is what the Identiverse summit panel meant by 'not a policy system' and what WorkOS meant by the gateway being undefined. Anything of that kind is routed to the new extension model, optional and additive, in a separate repository. This page is the baseline against which the summit's forecast, that the specification gains a delegated-identity mechanism within a year, will be graded.
  7. 7BI-FIND-2026-0276 · MCP made authorization optional, and two identity veterans say most servers took the optionThe Model Context Protocol specifies OAuth for authorization and leaves it optional, and the people who build identity products say most servers take the option. On this show the head of SecureAuth and the engineer who open-sourced Cedar agree on the mechanism: a software vendor under pressure to ship an MCP server wraps the API it already has, so the fine-grained scopes an agent needs were never there to expose. Their phrase is that it is a big, fat, raw API play. They name no server and give no count. The specification text we read confirms the opening: authorization is optional, and a client that does use it is a plain OAuth client with no delegation.
  8. 8BI-FIND-2026-0263 · Okta's answer to agent sprawl: put the identity provider between every agent and every appThe April 2026 Vercel breach is turning into the vendor reference case for agent tokens, and it is growing in the telling. Kahn describes an unnamed vibe-coding company that lost its entire source code through a long-lived, over-privileged token belonging to a third-party agent. The public account is that an infostealer at the AI vendor Context.ai exposed OAuth tokens it stored, which opened a Vercel employee's Google account, and that Vercel lost some source code, environment variables and a limited set of customer credentials. The mechanism he names is accurate. The scale is not what was reported.
  9. 9BI-FIND-2026-0482 · A phishing agent hosted on Microsoft's own domain, and why giving agents identities does not stop itCoPhish, published by Datadog Security Labs on 20 October 2025, turns a Copilot Studio agent into a phishing page that lives on copilotstudio.microsoft.com. The attacker builds an agent, points its sign-in step at the consent screen of an app the attacker registered, and adds an action that forwards the token from Microsoft's servers once the victim approves, so nothing suspicious crosses the victim's browser and MFA never comes into it. Datadog's demo app asked for Mail.ReadWrite, Mail.Send and Notes.ReadWrite, which an ordinary user could still grant under Microsoft's default consent policy; an application administrator could be talked into granting anything. Microsoft treats it as social engineering rather than a vulnerability.
  10. 10BI-FIND-2026-1473 · From Level 2 up, OWASP's AI security standard asks for an identity per agent and a check on every MCP tool callIn the published AISVS 1.0, the requirements an identity team would own sit in three chapters. The agentic chapter (C9) asks for a unique cryptographic identity per agent instance, a scope-limited token that carries the user's authorization to every downstream call, and access decisions made by application logic or a policy engine, "never by the AI model itself". The MCP chapter (C10) has servers validate the access token on each request under OAuth 2.1, check both the tool and its argument values on every invocation, and never pass a client's token through to downstream APIs. The Access Control and Identity chapter (C5) holds 11 requirements, among them step-up authentication for risky AI operations and the end user's permissions enforced inside retrieval pipelines. Levels decide who has to meet these: the agent identity, delegation and per-invocation rules above are Level 2, C10's basic token checks are Level 1, and C5's step-up and federated agent token rules are Level 3, so an assessment at Level 1 covers little of this. On stage, Jim Manico gave the reason MCP has its own chapter: "models don't make security decisions."
  11. 11BI-FIND-2026-1523 · AAuth carries the signals an agent's approval needs, Hardt says; the brain that decides does not exist yetHardt, who says he is working on OAuth 2.1, says it adds no new features and does not make proof of possession a required piece either. On the web, he says, TLS lets a client know which server it reached, but "the server has no idea who's calling it". He traces the wider problem to OAuth being "a framework as opposed to a protocol", with no conformance on what a client must do to work with a given server. In AAuth every HTTP call is signed, so the server knows the caller, and he says the same signing could give webhooks a standard alternative to the shared secrets they rely on today.
  12. 12BI-FIND-2012-0004 · RFC 6749 admits a server can't tell who presents a token; the fixes arrived in 2020 and 2023RFC 6749 gives a resource server no way to tell whether the client presenting an access token is the client it was issued to. Section 10.3 says so in as many words: the specification "does not provide any methods for the resource server to ensure that an access token presented to it by a given client was issued to that client by the authorization server." It leaves token types to companion documents (§7.1), and the companion published with it, RFC 6750, defines the bearer token that works for whoever holds it. We read the later binding standards as answers to this gap, each published as a separate, optional document: certificate-bound tokens over mutual TLS in RFC 8705 (2020), DPoP in RFC 9449 (2023), and in RFC 9700 (2025) a SHOULD, not a MUST, that servers sender-constrain access tokens.
  13. 13BI-FIND-2012-0008 · RFC 6749 admits a server can't tell who presents a token; the fixes arrived in 2020 and 2023RFC 6749's delegation is one hop. A resource owner approves a third-party client, and the authorization server issues that client an access token (§1); or a confidential client gets a token with only its own credentials, which the RFC says is typically the client acting on its own behalf (§1.3.4, §4.4). The RFC's text uses the word "agent" only inside "user-agent", which it describes as typically a web browser. It does define the hook that later delegation work plugs into: an extension grant is any absolute URI sent as grant_type (§4.5). The JWT bearer grant (RFC 7523) and token exchange (RFC 8693) are grants of that kind. Our briefing on the 2026 identity-assertion grant draft found that it profiles both, and its appendix walks through an AI agent as the OAuth client.
  14. 14BI-FIND-2012-0006 · RFC 6749 admits a server can't tell who presents a token; the fixes arrived in 2020 and 2023Several protections that later RFCs tightened sit in RFC 6749 as conditions or examples. Only public clients and confidential clients using the implicit grant must register a redirect URI; for others it is a SHOULD (§3.1.2.2). The server should ask for the complete URI, and if it cannot, it should at least require scheme, authority and path. Simple string comparison is required when the full URI was registered; otherwise the server matches against the registered parts (§3.1.2.3). For a public client, the code is checked against the client_id in the request (§4.1.3), which the RFC says is not a secret (§2.2). Even TLS on the redirection endpoint is a SHOULD, because in 2012 requiring it was "a significant hurdle for many client developers" (§3.1.2.1). Refresh token rotation appears in §10.4 only as an example of how a server could detect abuse when it cannot authenticate the client. Among the later RFCs we have read, PKCE (RFC 7636, 2015) has the client prove at the token endpoint that it holds a one-time key it created for that authorization request, and RFC 9700 (2025) requires exact redirect matching and sender-constrained or rotated refresh tokens for public clients.
  15. 15BI-FIND-2013-0008 · RFC 6819 warned in 2013 that servers receiving a token may reuse it, and offered audience binding and client-bound tokensRFC 6819 does not rank its threats. It says it cannot assess the probability or risk of a threat, because both depend on the application and deployment, and offers itself as a foundation for deployment-specific threat models. It also makes the end user part of the security model, while conceding that users often cannot judge what they approve. For malicious user-installed apps that steal credentials, over-request scope or approve on the user's behalf, section 5.5 offers no fix: "No solution is offered here, because none is known."

›In our briefings

The claim each of the newest briefings on OAuth would have you leave with.

  1. An MCP Events subscription inherits none of the limits on the access token that created it, which is short-lived, narrow in scope and checked on every request. The draft's design sketch keys a webhook subscription on the principal, the delivery URL, the event name and its arguments; the token, its scopes and its expiry are not part of that key. The principal MUST be authenticated and authorized at subscribe time, and after that the sketch says the server 'SHOULD periodically re-verify permissions'. WorkOS's Maria Paktiti: "There is no interval, no MUST, and no conformance test behind it." The lifetime is negotiable up to no expiry: ttlMs: null requests a subscription that never expires, and a server that grants it returns refreshBefore: null, so no refresh comes. Hence her line that 'the TTL you grant is your revocation window'. In her worked example, IT revokes a departing employee's access to a customer-contracts folder on Monday morning and the 24-hour subscription's next refresh lands Tuesday morning; a server that checked only at subscribe time, which is all the draft strictly requires, delivers every contract edit in between [figure 2].

    ChatGPT's MCP event subscriptions outlive the token that created them, and the draft sets no re-check scheduleBI-FIND-2026-0401

  2. The WorkOS CLI writes its MCP server into a coding agent only when the user opts in: the setup offer it may show after workos auth login or workos install defaults to No and stops asking once declined, a non-interactive, CI or --json run installs nothing, and opting in takes an explicit command such as workos mcp install or workos setup --yes. Once connected, the agent acts as the person who signed it in. Paktiti writes that the agent "inherits your dashboard role and can only do what your account is allowed to do." It works against one environment at a time, starts in a sandbox environment, and operates on production only when the user tells it to. Teams that want tighter limits get three independent admin settings (Enable, Allow production access and Allow write access), and all three are on by default. Apart from those settings and the sandbox default, the post describes no way to give the agent less than the user's own role.

    Opt in to WorkOS's MCP server and your coding agent acts as you, with write and production access on by defaultBI-FIND-2026-2401

  3. Okta's and Microsoft's competing SCIM drafts for AI agents have given way to one joint draft, and no IETF working group has taken it up. In June 2026 Mark Wahl and Pamela Dingle of Microsoft, Danny Zollner of Okta and Ismael Kazzouzi of Nextident filed draft-wzdk-scim-agent-resource-00, an informational draft that defines the agent as its own SCIM resource type. WorkOS calls the joint authorship "a real signal of forming consensus". The datatracker lists it as an individual submission that replaces neither earlier draft; both of those have expired, and this one expires on 7 December 2026. WorkOS says the October 2025 Okta draft by Abbey and Cohen modelled agents through an "agentic application" instead of as their own resource. As filed, that draft already defines Agent as its own resource type, related to an agentic application as owned, authorized or guest, and the SCIM working group's IETF 125 slides say both drafts represented agents as a resource type. The joint draft's text never mentions the Okta draft or agentic applications, and it has none of the Okta draft's certificate, protocol or OAuth configuration attributes, so we would not call it a merger of the two texts. An agent governance extension from an Oracle author, draft-kushwaha-scim-agent-governance-00, filed in July 2026, was also active on the datatracker; the post does not mention it.

    Okta and Microsoft now co-author one SCIM draft for AI agents, but no working group has taken it upBI-FIND-2026-0407

›Cited in 343 briefings

Every briefing that discusses this term, newest first.

  1. ChatGPT's MCP event subscriptions outlive the token that created them, and the draft sets no re-check schedule

    Article · · WorkOS Blog · Maria Paktiti · Oct 1, 2026

  2. Opt in to WorkOS's MCP server and your coding agent acts as you, with write and production access on by default

    Article · · WorkOS · Maria Paktiti · Sep 30, 2026

  3. Okta and Microsoft now co-author one SCIM draft for AI agents, but no working group has taken it up

    Article · · WorkOS Blog · Maria Paktiti · Sep 30, 2026

  4. Uber runs per-hop token exchange with a full actor chain for AI agents in production

    Article · · Uber Engineering blog · Matt Mathew et al. · May 21, 2026

  5. OMB tells agencies their API gateways must issue post-quantum signed tokens

    Article · · Office of Management and Budget (whitehouse.gov) · Russell T. Vought et al. · Jun 24, 2026

  6. CSA's John Yeoh expects lifecycle management to be the first agent control to break

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : The Next 24 Months · Sep 7, 2026

  7. When AI agents hand work to other agents, the person who started the job can get lost

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : Governing AI · Sep 7, 2026

  8. Phishing links that start at a real Microsoft or Google sign-in address and end at the attacker's

    Article · · Microsoft Security Blog · Microsoft Defender Security Research Team · Mar 2, 2026

  9. MCP's July spec ties client credentials to the authorization server that issued them

    Article · · Model Context Protocol project · Jul 28, 2026

  10. Singapore's regulator: each AI agent should have its own identity and, as a rule, no more access than its user

    Article · · Infocomm Media Development Authority (Singapore) · May 20, 2026

  11. A paper's 90- and 180-day rules for machine identities come with no test behind them

    Article · · International Journal For Multidisciplinary Research (Vol 8, Issue 3) · Thrinaath Vajragowni · May 23, 2026

  12. A disabled agent's old tokens still pass every check; a DNS draft now asks receivers to time how long

    Draft · · IETF Datatracker · Sriram Shankarlingam, HexaEight · Oct 20, 2026

  13. AAuth gives every agent its own key, then keeps the delegation chain out of the token on purpose

    Draft · · IETF Datatracker · Dick Hardt, Hellō · Sep 25, 2026

  14. Asor's agent-chain draft now says a chain keeps verifying after its principal leaves, until expiry or revocation

    Draft · · IETF Datatracker · Rafael Asor · Oct 28, 2026

  15. OAuth's token revocation list nears RFC, and a shared list hides which token is checked

    Draft · · IETF Datatracker · Tobias Looker et al. · Aug 13, 2026

  16. Transaction Tokens carry who started a request through internal services and define no list of the hops in between

    Draft · · IETF OAuth Working Group · Atul Tulshibagwale et al. · Jul 30, 2026

  17. The OAuth working group split over a token-binding draft that never says what DPoP lacks

    Draft · · IETF Datatracker · Justin Richer et al. · Jul 28, 2026

  18. OAuth's draft for crossing trust domains is approved for publication and never says agent

    Draft · · IETF OAuth Working Group · Arndt Schwenkschuster et al. · Jul 19, 2026

  19. The JWT an agent or other OAuth client signs in with may name only the server's issuer, never the token endpoint

    Draft · · IETF Datatracker · Michael B. Jones et al. · Apr 28, 2026

  20. An AI agent can do its damage within one session, so a practitioner wants a kill switch on its whole identity

    Podcast · · Identity Decoded · Beyond the vault: Why AI agents force us to rethink Privileged Access Management (PAM) · Jul 15, 2026

  21. A new STIR draft would let a number's holder require AI agents calling from it to say so

    Draft · · IETF Datatracker · Jon Peterson, TransUnion · Nov 2, 2026

  22. Hassan's agent delegation draft now classes granting access as execute, not write

    Draft · · IETF Datatracker · Amr Hassan · Oct 22, 2026

  23. A user's approved request is not yet authority an agent can be held to, and most deployments skip that step

    Article · · Control Plane by Karl McGuinness · Karl McGuinness · Mar 17, 2026

  24. OAuth token exchange does not guarantee a sub-agent stays inside its parent's access

    Article · · Control Plane by Karl McGuinness · Karl McGuinness · Mar 18, 2026

  25. Enforced SMB and LDAP signing did not stop NTLM relay until Microsoft's September and October 2026 patches

    Podcast · · Risky Business · #859 · Nov 11, 2026

  26. OWASP's AIVSS lifts a CVSS 2.1 agent flaw to 7.1, and all ten worked examples land High or Critical

    Article · · OWASP AIVSS project · Ken Huang et al. · Oct 22, 2026

  27. W3C's JOSE and COSE rules for credentials admit there is no standard way yet to fetch a JWK from a DID URL

    Article · · W3C · Michael Jones et al. · Oct 13, 2026

  28. MCP's November 2025 security guide makes proxy servers ask consent for each client before forwarding a login

    Article · · Model Context Protocol · Model Context Protocol project · Nov 25, 2025

  29. Backstage gives an agent a token that names only its user, so the agent can run anything the user can

    Video · · CNCF [Cloud Native Computing Foundation] · Uploaded November 10, 2026

  30. Sello has the services an AI agent calls sign its receipts; the agent can't fake them, but it can go around them

    Paper · · arXiv · Juan Figuera · Jun 2, 2026

  31. An agent-mandate draft checks who may delegate, and now intends to carry its chain in Asor's format

    Draft · · IETF Datatracker · Claudiu Hulea, Braincap SRL · Oct 24, 2026

  32. Agent-audit draft now admits a call on the principal and the current agent, as RFC 8693 requires

    Draft · · IETF Datatracker · Shameer Thaha et al. · Oct 19, 2026

  33. ceLLMate checks a browser agent's HTTP requests, not its clicks, and blocked all 12 scripted GitLab attacks

    Paper · · arXiv · Luoxi Meng et al. · Dec 14, 2025

  34. Okta and Google tie an agent's calls to the user, while GitHub's shared Copilot automations now act as Copilot

    Release tracker · · 11 vendors' release notes · Oct 2026

  35. MCP's client credentials extension puts the secret in the form body, while its server rule names HTTP Basic

    Article · · Model Context Protocol project · Oct 23, 2026

  36. LiteLLM left a leaked admin key live; its first reported use, 136 days on, yielded an org owner's GitHub token

    Article · · LiteLLM blog · Oliver Jensen et al. · Oct 23, 2026

  37. An IETF draft says root admins cannot spoof its credential; its security section is still a placeholder

    Draft · · IETF Datatracker · Eric Voit et al. · Oct 30, 2026

  38. A Nokia and China Mobile draft finds A2A and MCP stop at one hop, and wants cancellation carried down the chain

    Draft · · IETF Datatracker · Tirumaleswar Reddy.K et al. · Oct 27, 2026

  39. An OAuth client gets to name who vouches for it, and removing one waits on server caches

    Draft · · IETF Datatracker · Karl McGuinness · Sep 28, 2026

  40. Register a platform's identity provider once, not each agent: trust rests on its issuer, with no revocation

    Draft · · IETF Datatracker · Paul Carleton et al. · Sep 22, 2026

  41. An OAuth draft lets the API, not the agent, describe the approval, and now name the key the token is bound to

    Draft · · IETF Datatracker · Yaroslav Rosomakho et al. · Jun 25, 2026

  42. WIMSE's agent draft adds how an agent's access ends and where policy engines fit, without a new requirement

    Draft · · IETF WIMSE Working Group · Pieter Kasselman et al. · Sep 15, 2026

  43. OAuth's URL client ID draft tightens server rules in -03; the client is still whoever controls the URL

    Draft · · IETF Datatracker · Aaron Parecki et al. · Jul 6, 2026

  44. OAuth's SPIFFE draft opens metadata URLs to all three credentials and says what a self-served key cannot prove

    Draft · · IETF Datatracker · Arndt Schwenkschuster et al. · Jun 15, 2026

  45. WorkOS's agent checklist limits a delegated agent to what it and its user may both do, checked on every call

    Article · · WorkOS Blog · Maria Paktiti · Sep 30, 2026

  46. JPMorgan won't let some agent sessions read and send email at once, says its security architect

    Podcast · · Insecure Agents · "Is This Tool Call Allowed? It's Never That Simple": Michael Davis (J.P. Morgan) · Sep 9, 2026

  47. Cisco's SD-Card rewrite pins MCP tools to what a registry signed; its security sections still read TODO

    Draft · · IETF Datatracker · Suhas Nandakumar et al. · Nov 1, 2026

  48. An agent audit draft says the agent is not trusted, yet lets the agent's operator run the audit store

    Draft · · IETF Datatracker · Mirja Kühlewind et al. · Sep 7, 2026

  49. Raut's revised agent draft keeps token exchange out of the model's reach, and concedes the token carries no evidence of it

    Draft · · IETF Datatracker · Ashay Raut · May 22, 2026

  50. An unadopted AGTP draft would let gateways refuse an agent's out-of-scope requests from its TLS certificate

    Draft · · IETF Datatracker · Chris Hood, Nomotic, Inc. · Oct 30, 2026

  51. OAuth's draft for token requests that wait on a person now gives the client a link for the user to approve

    Draft · · IETF Datatracker · Guilherme de Oliveira Niero et al. · Sep 23, 2026

  52. Sweeney's delegation draft concedes its server is trusted with users' credentials, and drops an interop claim

    Draft · · IETF Datatracker · Kieran Sweeney · Oct 13, 2026

  53. Cross-App Access draft warns that one stolen sign-in token could reach every app the identity provider permits

    Draft · · IETF Datatracker · Aaron Parecki et al. · May 21, 2026

  54. Give an agent access for the task and take it back afterwards, four voices say, and four say people approving each request cannot keep up

    Field signals · · 8 voices from the field · Feb 2026 to Oct 2026

  55. RFC 9207's issuer check stops at the redirect, and n8n's token-exchange flaw sat just past it

    Article · · WorkOS · Maria Paktiti · Jul 20, 2026

  56. A China Mobile draft lets agents skip the user for pre-approved services but doesn't say how an agent proves who it is

    Draft · · IETF Datatracker · Zongpeng Du, China Mobile · Oct 27, 2026

  57. IETF workload practices draft describes single-audience JWTs in place of stored secrets and discourages token exchange

    Draft · · IETF Datatracker · Arndt Schwenkschuster et al. · Sep 22, 2026

  58. Global Token Revocation must end a user's refresh tokens; their access tokens can outlive the call

    Draft · · IETF Datatracker · Aaron Parecki, Okta · Feb 25, 2026

  59. AGTP checks that an agent ID is signed; binding it to the connection is an add-on in the author's patent notice

    Draft · · IETF Datatracker · Chris Hood, Nomotic, Inc. · Jun 28, 2026

  60. OAuth adopts Delegate SD-JWT, which traces each hand-off to the issuer but never checks that authority narrowed

    Draft · · IETF Datatracker · Gareth Oliver et al. · Apr 22, 2026

  61. Each agent and each tool call can pass its check while the system fails, an Oxford-led survey argues

    Paper · · arXiv · Christian Schroeder de Witt · Apr 29, 2026

  62. Agent URI draft -04 ties an agent's name to a key document and bars OAuth servers from trusting the name alone

    Draft · · IETF Datatracker · Yaswanth Narvaneni et al. · Oct 20, 2026

  63. Agent delegation records not anchored in trusted time become deniable once timestamps can be forged

    Draft · · IETF Datatracker · V.K. Uppalapati · Sep 29, 2026

  64. Drake's revised draft: an agent identity outlives its operator but is never reissued once its last key is gone

    Draft · · IETF Datatracker · Christopher Drake, 1id.com · Sep 25, 2026

  65. Niyikiza's agent tokens narrow to a tool's arguments offline; revision -02 breaks -01 implementations

    Draft · · IETF Datatracker · Niki Aimable Niyikiza · Jun 15, 2026

  66. Attackers treat AI keys as production credentials, Anthropic's September misuse report says

    Article · · Anthropic · Anthropic Threat Intelligence team · Sep 10, 2026

  67. MCP's November 2025 authorization spec puts metadata documents ahead of dynamic client registration

    Article · · Model Context Protocol · Nov 25, 2025

  68. Drake's agent registry names who may issue an agent's token, and its answer has no signature of its own

    Draft · · IETF Datatracker · Christopher Drake, 1id.com · Sep 25, 2026

  69. One global registry for AI agent identities, and no one allowed to switch an identity off

    Draft · · IETF Datatracker · Christopher Drake, 1id.com · Oct 27, 2026

  70. OAuth tokens prove an agent's rights, not a person's consent; revision 05 adds a day-long grant with spend caps

    Draft · · IETF Datatracker · Meiling Chen et al. · Oct 27, 2026

  71. A May 2025 agent-protocol framework, renamed twice and still unadopted, lists identity needs but no mechanism

    Draft · · IETF · Jonathan Rosenberg et al. · Jul 4, 2026

  72. OAuth scopes grant agents far more than the task needs, four voices say, and authorization handed from agent to agent has no settled pattern yet

    Field signals · · 7 voices from the field · Oct 2025 to Oct 2026

  73. A cross-domain transaction-token grant now names AI agents as a use and keeps the call chain at home

    Draft · · IETF Datatracker · George Fletcher et al. · Sep 10, 2026

  74. SailPoint says its agent plan check can deny deletion in a file-creation task

    Video · · SailPoint · Oct 16, 2026

  75. Visa’s agent-written patches still need human acceptance and attack-path validation

    Podcast · · AI Security Podcast · How Visa Secures Trillions Using AI Agents & Open-Source Harnesses · Oct 2, 2026

  76. SailPoint’s JIT demo separates approved eligibility from expiring activation

    Video · · SailPoint · Oct 16, 2026

  77. MCP client setup moves from registration to metadata checks in a Spring walkthrough

    Video · · OWASP Foundation · Oct 24, 2026

  78. A routing-policy draft requires authenticated links before hop checks can prove a chain

    Draft · · IETF Datatracker · Sumit P. Ahuja, Main Labs · Oct 21, 2026

  79. Apps staff build with AI app builders leave a trail in certificate logs and DNS, a Cerebras security lead says

    Video · · OWASP Foundation · Uploaded October 21, 2026

  80. IBM Research puts agent identity in a SPIFFE and OAuth sidecar; Maia Iyer calls authorization policy still open

    Podcast · · Kubernetes Bytes · Your AI Agent Has Too Much Access | Fixing Agent Identity · Sep 15, 2026

  81. Barclays mandates one gateway for its agents' budgets, blocks and audit, and its AI engineering director says the setup is not yet tested at scale

    Podcast · · Insecure Agents · The Fishbowl Problem: Agent Identity Across Clouds and Vendors, with Andy McMahon (Barclays) · Oct 5, 2026

  82. Delegation receipts for AI agents, revision 15: holding a copy of a receipt no longer lets you extend the chain

    Draft · · IETF Datatracker · Ryan Nelson, Authproof · Oct 22, 2026

  83. AAuth carries the signals an agent's approval needs, Hardt says; the brain that decides does not exist yet

    Podcast · · Collateral Dialogue · Self-Driving Software: What OAuth Can’t Do for AI Agents | Dick Hardt, Hello · Sep 2, 2026

  84. The OWASP MCP Top 10 lead says few security teams can find the MCP servers developers run on their own machines

    Podcast · · The Application Security Podcast · Shadow MCP Servers: The AI Security Risk Hiding on Your Developers' Laptops · Oct 12, 2026

  85. At OWASP, one poisoned memory entry made a demo agent send a Q4 report to an attacker server

    Video · · OWASP Foundation · Recorded Jun 2026 · Uploaded October 21, 2026

  86. From Level 2 up, OWASP's AI security standard asks for an identity per agent and a check on every MCP tool call

    Video · · OWASP Foundation · Oct 21, 2026

  87. Agents would show a signed user goal with each OAuth scope request; the draft leaves open how the server checks it

    Draft · · IETF Datatracker · Meiling Chen et al. · Oct 19, 2026

  88. RFC 9943 makes a log prove who signed a statement, not that it is true or that nothing was left out

    Article · · IETF (RFC Editor) · Henk Birkholz et al. · Jun 30, 2026

  89. SaaS apps that only know users end up giving agents human accounts, says Okta's former chief architect

    Podcast · · The Identity Jedi Show: Where Identity Meets Strategy · Agents need a mission, not a key. · Oct 21, 2026

  90. The IETF's stronger workload proof is built for the proxy in the middle, and it still leaves replay protection optional

    Draft · · IETF Datatracker · Joseph A. Salowey et al. · Oct 20, 2026

  91. ChainIT's design has the payment rail rebuild each payment's hash before money moves; the paper reports no test

    Paper · · arXiv · Jeremy Blackburn et al. · Oct 16, 2026

  92. An individual IETF draft takes a workload's role and group out of its name and puts them in separate metadata

    Draft · · IETF Datatracker · Shlomo Zalman Heigh et al. · Oct 16, 2026

  93. Six companies' agent-auth draft, since adopted by the WIMSE group, keeps credentials out of the model's reach

    Draft · · IETF Internet-Draft (individual submission, since adopted by the WIMSE working group) · Pieter Kasselman et al. · Jul 6, 2026

  94. OpenID's AuthZEN API can't say an agent acts for someone, and its policy service trusts whatever the app sends

    Article · · OpenID Foundation · Omri Gazitt et al. · Jan 11, 2026

  95. An OAuth agent profile has the token server block any widening of scope, and leaves revoking the chain optional

    Draft · · IETF Datatracker · Sanjeev Kumar, Orchestrum Technologies LLP · Aug 30, 2026

  96. Nothing carries a person's limits on an agent through to the moment it acts, Yossif's problem statement argues

    Draft · · IETF Datatracker · Mohamad Khalil Yossif · Jul 22, 2026

  97. An OAuth profile for AI agents makes every hand-off cut privileges, but a shorter expiry alone counts as a cut

    Draft · · IETF Datatracker · Angel Cruz · Feb 7, 2026

  98. Anthropic asks for per-agent identity; its guide leaves Claude Code sub-agent credentials unspecified

    Article · · Anthropic (Claude) · Anthropic · May 27, 2026

  99. Anthropic says agents should never use static API keys, yet its sub-agents can carry the parent's permissions

    Article · · Anthropic · Anthropic · May 18, 2026

  100. OpenID Federation 1.0 lets each level of a trust chain only tighten the rules, and defines no revocation process

    Article · · OpenID Foundation · Roland Hedberg et al. · Feb 17, 2026

  101. A transparency-log profile for agents exposes edited and dropped records; an action nobody logged leaves no gap

    Draft · · IETF Datatracker · Pinar Emirdag et al. · Oct 12, 2026

  102. Human Delegation Provenance is now an audit record only, and one that cannot prove it is complete

    Draft · · IETF Datatracker · Asiri Dalugoda, Helixar · Oct 6, 2026

  103. An end-to-end encrypted draft would hide an AI agent's task from the broker, but not who sent it or to whom

    Draft · · IETF Datatracker · Hamdy Atakora, Imara Labs · Sep 21, 2026

  104. Bu's checklist names a verifier for each agent-protocol claim and checks 'the same agent as before' separately

    Draft · · IETF Datatracker · Songbo Bu · Oct 14, 2026

  105. An attested OAuth client is one somebody vouched for; revision 12 says to trust its claims only as far as the voucher

    Draft · · IETF Datatracker · Tobias Looker et al. · Oct 13, 2026

  106. In Huawei's reworked OAuth draft, evidence signed by the token's subject can narrow access but never widen it

    Draft · · IETF Datatracker · Cheng-Kang Chu et al. · Sep 1, 2026

  107. World's maker proposes a site-scoped handle for each verified human, and bars using it alone to log anyone in

    Draft · · IETF Datatracker · Aurélien Brézun, Tools for Humanity · Aug 6, 2026

  108. Huawei's OAuth draft for teams of agents enforces its firm limit on authority only in an optional mode

    Draft · · IETF Datatracker · Yurong Song et al. · Jul 1, 2026

  109. Okta's expired SCIM agent draft recorded certificates and OAuth clients; the joint draft after it dropped both

    Draft · · IETF Datatracker · Macy Abbey et al. · Oct 16, 2025

  110. A decentralized ID design for agents proves who is liable but can collect only from collateral locked in advance

    Paper · · arXiv · Ahammod Munim Ramil et al. · Oct 12, 2026

  111. A planted page note got browser agents to authorize access in all 73 attack runs; a server-side check stopped it

    Paper · · arXiv · Md Imran Hossen · Oct 10, 2026

  112. Berkeley and IBM found six ChatGPT and Claude connector setups asking more than their advertised tools need

    Paper · · arXiv · Jinhao Zhu et al. · Dec 11, 2025

  113. Schrock's receipts prove a named key approved one exact agent action, and the draft lists at length what they cannot prove

    Draft · · IETF Datatracker · Iman Schrock, EMILIA Protocol · Sep 12, 2026

  114. Eve Maler says the push to give every AI agent a responsible human misses agents a company does not own

    Podcast · · Identity at the Center · #453 - Treating Identity Like a Product with Eve Maler · Oct 12, 2026

  115. The PEDIGREE draft has verifiers re-check every ancestor of an agent's token, without saying how to fetch them

    Draft · · IETF Datatracker · Karthik Rampalli, Glyphzero Labs · Apr 25, 2026

  116. OpenA2A's draft aims to keep secrets from the agent, and says no implementation yet supports its new controls

    Draft · · IETF Datatracker · Abdel Fane, OpenA2A · Oct 2, 2026

  117. Before an agent pays or changes data, Schrock's last check treats it as untrusted and keeps the record itself

    Draft · · IETF Datatracker · Iman Schrock, EMILIA Protocol · Sep 26, 2026

  118. The signing-key draft under AAuth offers eight ways to trust a key, and only one says who the agent works for

    Draft · · IETF Datatracker · Dick Hardt et al. · Sep 13, 2026

  119. Two implementations stop at the last of Reece's ten cross-company rules: a person approving one specific action

    Draft · · IETF Datatracker · Morgan Reece · Aug 31, 2026

  120. A2A 1.0 connects agents across companies and leaves out the person they act for

    Article · · A2A Protocol (Linux Foundation) · A2A Protocol project et al. · May 28, 2026

  121. OpenA2A's protocol proves an agent holds a key and scores its behaviour, but never says who it works for

    Draft · · IETF Datatracker · Abdel Fane, OpenA2A · Oct 6, 2026

  122. Sharif's profile writes an AI agent's rights to pay and delete into an identity certificate valid up to a year

    Draft · · IETF Datatracker · Raza Sharif, CyberSecAI · Oct 2, 2026

  123. An MCP server picks the login URL its client opens, and that was enough to run code on users' machines

    Video · · Black Hat · Aug 20, 2026

  124. Auth0's own Claude Code tutorial runs the agent on the developer's login and hands it fifteen admin scopes

    Article · · Auth0 Blog · Manish Hatwalne · Sep 29, 2026

  125. The official MCP TypeScript SDK now binds tokens to keys, ahead of the spec it implements

    Article · · WorkOS Blog · Maria Paktiti · Sep 29, 2026

  126. TPX replaces an app's embedded AI provider key with a capped, metered grant the user approves at their provider

    Article · · tokenpony.dev · Alex Polvi · Jul 20, 2026

  127. OWASP's agent Top 10 blames identity systems built for people, and does not say how it chose or ranked its risks

    Article · · OWASP GenAI Security Project · John Sotiropoulos et al. · Dec 9, 2025

  128. Okta's Oktane keynote: two agent products generally available now, support for other identity providers in 2027

    Video · · Okta · Sep 23, 2026

  129. Okta's September videos: six customer stories with few measured results, and keynote recaps that drop the ship dates

    Channel digest · · Okta (Oktane) · Sep 2026

  130. NIST's agent identity work starts from OAuth, SPIFFE and SCIM and defers agents from outside the enterprise

    Article · · NIST National Cybersecurity Center of Excellence · Harold Booth et al. · Feb 5, 2026

  131. NIST and CISA advise one-hour tokens, 90-day keys and hardware key storage; AI agents get one paragraph

    Article · · NIST (CSRC) · Ryan Galluzzo et al. · Sep 15, 2026

  132. Saviynt's strategy head calls agent discovery a commodity and pitches Zuma for runtime control

    Podcast · · The Non-Human & AI Identity Podcast · Ep # 14 - Turning an AI Breach into a Case Study · Sep 15, 2026

  133. A draft ties what each AI agent may read to what it may do, and still can't take a grant back

    Draft · · IETF Datatracker · Hamdy Atakora · Sep 21, 2026

  134. DIF's agent spec names every AI agent by a DID; the IETF's Agent Name Service switched to domain names

    Article · · Decentralized Identity Foundation (KYA-OS) · Dylan Hobbs et al. · Jul 29, 2026

  135. Microsoft limits stolen refresh tokens by restricting where they can be used, not by binding the token itself

    Podcast · · Entra.Chat · Stolen Tokens, Agents and Universal CAE: What Global Secure Access Adds to Entra ID · Oct 9, 2026

  136. Corvic's own tests find its agent vault keeps keys out of prompts but does much less against a misused connector

    Paper · · arXiv · Kenney, Corvic AI · Sep 27, 2026

  137. In Accenture's agent-delegation design, no outside party checks the user, and revocation is left open

    Paper · · arXiv · Srikumar K. Subramanian et al. · Sep 25, 2026

  138. PayPal moved MCP tool permission checks into the server, and prompt-injected agents stopped getting through

    Paper · · arXiv · Huan Li et al. · Sep 18, 2026

  139. A survey rates only workload identity ready for agents, and argues no standard can tell what an agent intends

    Paper · · arXiv · Takumi Otsuka et al. · Apr 25, 2026

  140. A phishing agent hosted on Microsoft's own domain, and why giving agents identities does not stop it

    Article · · WorkOS Blog · Maria Paktiti · Sep 29, 2026

  141. Registering an MCP server on Bifrost ran its command, and the admin API that allowed it shipped with no password

    Article · · WorkOS Blog · Maria Paktiti · Sep 29, 2026

  142. Folding every hop's signature into one would stop anyone stripping a signed hop out of an agent's request

    Draft · · IETF Datatracker · Tirumaleswar Reddy.K et al. · Sep 28, 2026

  143. AAuth's R3 lets an agent ask for an API's named operations, and a person approve one exact call

    Draft · · IETF Datatracker · Dick Hardt · Sep 28, 2026

  144. Hardt's AAuth Budgets caps what an agent may spend at each resource, and hides the person's real limit from it

    Draft · · IETF Datatracker · Dick Hardt · Sep 28, 2026

  145. Coetzee's agent token is good for one declared call, and the hard part is hashing that call the same way twice

    Draft · · IETF Datatracker · Rudolf Jacobus Coetzee · Jul 19, 2026

  146. A SANS instructor's broker vaults agents' real keys, but its third delivery model breaks the abstract's promise

    Draft · · IETF Datatracker · Kenneth G. Hartman · Mar 29, 2026

  147. An integrator builds agent access on OpenID Connect and OAuth; clients want one view across many MCP gateways

    Podcast · · Identity Unfiltered · CIAM, Agentic AI & the Future of Identity · Oct 5, 2026

  148. Transaction tokens are nearly a standard, and there is still no agreed place in them for the agent

    Podcast · · Identity at the Center · #449 - Decoded - Transaction Tokens with George Fletcher · Sep 21, 2026

  149. Opal's access-review AI runs with a person approving by default, and an Opal engineer still reads the rejections

    Podcast · · Identity at the Center · #448 - Sponsor Spotlight - Opal Security · Sep 17, 2026

  150. WorkOS's Tobin South, in November 2025: agents will get a new kind of account, not a new identity standard

    Podcast · · CodingCat.dev Podcast · 5.10 - How to Secure AI - Identity Access Management for Agents · Nov 21, 2025

  151. Strip the agent hype and one requirement is new: the chain back to the person who started the job.

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : Secure by Design · Sep 7, 2026

  152. A draft token hides some claims, works with old servers unchanged, and leaves agent delegation claims visible

    Draft · · IETF Datatracker · Su-hyeon Forten Lee · Oct 3, 2026

  153. Cisco's SD-Card puts an A2A Agent Card in a selective-disclosure token, and leaves its registry out of scope

    Draft · · IETF Datatracker · Suhas Nandakumar et al. · Mar 2, 2026

  154. Eight panels agree an agent acts for a person, never as that person. When agents hand work to other agents, nobody had an answer.

    Conference · · Las Vegas · June 2026, a one-day summit track inside Identiverse 2026; the eight panels were published as podcast episodes between 18 August and 7 September 2026

  155. A third SCIM agent draft gives the agent five lifecycle states, a quarantine, and an archive it can never leave

    Draft · · IETF Datatracker · Saurabh Kushwaha, Oracle · Jul 27, 2026

  156. Three MCP auth flaws in a month, and the spec had already written the rule the SDKs skipped

    Article · · WorkOS Blog · Maria Paktiti · Oct 2, 2026

  157. The IETF's simplest workload proof proves the key and leaves the request unprotected, and the draft says so itself

    Draft · · IETF Datatracker · Brian Campbell et al. · Aug 27, 2026

  158. OAuth handles an agent in one company, working while you watch. The OpenID paper says that is where it stops.

    Article · · OpenID Foundation · Tobin South et al. · Oct 2025

  159. The IETF's workload-identity architecture gives AI agents one subsection, calling an agent a delegated workload

    Draft · · IETF Datatracker · Joseph Salowey et al. · Jul 6, 2026

  160. The 'intent' in the Agentic JWT draft is a workflow step, and the agent reports its own fingerprint

    Draft · · IETF Datatracker · Abhishek Goswami · Jul 1, 2026

  161. The IBAC paper's strict mode blocked every prompt injection, and its agent finished only a third of its tasks

    Article · · ibac.dev · Jordan Potti · Mar 3, 2026

  162. MCP made authorization optional, and two identity veterans say most servers took the option

    Podcast · · Hybrid Identity Protection Podcast · Agentic AI and the Authorization Gap No One Closed · Jun 9, 2026

  163. Two ways to give an AI agent an OAuth identity clashed in April; a draft now lets them work together

    Podcast · · Hybrid Identity Protection Podcast · Securing Non-Human Identities in the Age of Agentic AI with Sarah Cecchetti, Director of Product Management at Semperis · Apr 28, 2026

  164. Okta's answer to agent sprawl: put the identity provider between every agent and every app

    Podcast · · Cloud Security Podcast · Who Governs Your AI Agents? Identity, Offboarding & Open Standards · Jul 2, 2026

  165. Keeping an agent's delegation chain is optional, and room in the HTTP header decides whether it survives

    Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : The New NHI Risk Reality · Aug 26, 2026

  166. An OpenID Foundation co-chair says AI agents need modest upgrades to today's identity systems, not a new one

    Podcast · · Identity at the Center · #390 - Identity Management for Agentic AI with Tobin South · Dec 8, 2025

  167. Mission-Bound OAuth's author now says the mission object does not belong in OAuth

    Article · · Control Plane by Karl McGuinness · Karl McGuinness · Mar 15, 2026

  168. Most of the work in Sierra's MCP gateway was identity: who each agent acts as and what it may reach

    Article · · Sierra Engineering · Mihai Parparita · Jul 22, 2026

  169. MCP's authorization spec makes the agent a plain OAuth client and leaves delegation to an extension

    Article · · Model Context Protocol project · Jul 28, 2026

  170. An MCP gateway can be demoed in a week; Sierra's rollout waited on the auth layer underneath it

    Article · · WorkOS Blog · Maria Paktiti · Sep 11, 2026

  171. Highflame's open-source ZeroID narrows an agent's token at every hop, a step we did not find in Uber's write-up

    Article · · Highflame (GitHub) · Sep 25, 2026

  172. The agent risk two CISOs fear is manipulation, not a stolen credential

    Podcast · · Defense in Depth · Identity and Access Management (IAM) in an Agentic AI World · Jul 23, 2026

  173. Ping moved agent identity from roadmap to shipping product, and let AI agents run its admin tools too

    Conference · · Ping Identity · Austin · 2-day event (Day 1 / Day 2), 2026

  174. Canva sandboxes bounded conversion jobs; broad workforce agents pose a different access problem

    Podcast · · AI Security Podcast · Why I Dont Trust Your AI Agent | Kane Narraway, Canva · Aug 20, 2026

  175. IPC passes a delegation chain between services; its signature proves only the last signer

    Draft · · IETF Datatracker · Ravi Kant Sharma, Ericsson · Jul 23, 2026

  176. xChk ships human OIDC portfolios and a separate agent approval API

    Paper · · arXiv · Sean MacGuire · Jul 15, 2026

  177. The browser OAuth draft favors a backend that keeps tokens out of JavaScript

    Draft · · IETF Datatracker · Aaron Parecki et al. · Jul 6, 2026

  178. A July OAuth draft keeps agent identity stable as keys rotate

    Draft · · IETF Datatracker · Karl McGuinness · Jul 5, 2026

  179. Batch delegation assigns each permission to an agent, then filters at token exchange

    Draft · · IETF Datatracker · Yuan Ni et al. · Jul 3, 2026

  180. In one author's MCP benchmark, a confirmation prompt on every call still let 6 of 10 attacks through

    Paper · · arXiv · Ting Liu, SymbolicLight · Jun 27, 2026

  181. One implementer found a transaction-token rule that let any scope through; the OAuth group fixed it in weeks

    Draft · · IETF Datatracker · Dhruv Agnihotri · Jun 23, 2026

  182. GM’s employee directory gave applications a reason to adopt single sign-on

    Podcast · · Identity Decoded | The Identity Security Podcast · From IT support to security's core: General Motors' identity story · Jun 17, 2026

  183. OpenID's AuthZEN group approves a draft that lets policy tell an agent 'not yet, and here is what is required'

    Article · · OpenID Foundation · Serj Hallam · Jun 15, 2026

  184. An OAuth draft lets device checks set an app's scopes; a first review found a copied app could reuse the result

    Draft · · IETF Datatracker · Efe Kahraman, Mekarge · Jun 9, 2026

  185. A June OAuth draft logs each hand-off between AI agents, but the per-hop limits the act claim lacks are optional

    Draft · · IETF Datatracker · Dapeng Liu et al. · Jun 8, 2026

  186. Huawei researchers add agent delegation to an existing permission model and prove each action traces to a human

    Paper · · arXiv · Amjad Ibrahim et al. · Jun 2, 2026

  187. Google's agent registry went GA in June while Okta, SailPoint and Ping pulled agents into their own lists

    Release tracker · · 11 vendors' release notes · Jun 2026

  188. Putting AIRGuard's policy in an agent's prompt barely cut attacks; enforcing it before each tool call did

    Paper · · arXiv · Suliu Qin et al. · May 27, 2026

  189. Atlassian's first draft for offline delegation banned bearer handles; revision 05 just recommends sender binding

    Draft · · IETF Datatracker · Larry Zhu et al. · May 22, 2026

  190. An AI agent's refused action can be approved only by someone its mandate names, says a revised draft

    Draft · · IETF Datatracker · Lars Kersten Kroehl, CryptoKRI GmbH · May 21, 2026

  191. 114 of 119 MCP servers that let outsiders register an OAuth client let them choose where sign-in codes are sent

    Paper · · arXiv · Huijun Zhou et al. · May 21, 2026

  192. A preprint cuts off every sub-agent within about 40 seconds of its parent stopping, with no revocation server

    Paper · · arXiv · Saurabh Deochake, SentinelOne · May 20, 2026

  193. WorkOS hands a personal AI agent a key its user owns, then contradicts itself on whether the key can be narrower

    Article · · WorkOS Blog · Maria Paktiti · May 15, 2026

  194. A proposed standard for agent authority advises against delegating it across company lines by default

    Paper · · arXiv · Partha Madhira · May 12, 2026

  195. AgentDID checks an AI agent's identity and readiness in 13.5 seconds, but was tested on at most 50 agent pairs

    Paper · · arXiv · Minghui Xu et al. · Apr 28, 2026

  196. China Mobile's agent-revocation draft adds security rules but still never says how it finds the sub-agents

    Draft · · IETF Datatracker · Meiling Chen et al. · Apr 27, 2026

  197. An Imperial and Oxford protocol would give AI agents one approved use of a secret, never the secret itself

    Paper · · arXiv · Xiaohang Yu et al. · Apr 27, 2026

  198. A 'decentralized' agent identity draft blocks risky calls when its Registry is down, and did:aip is taken

    Draft · · IETF Datatracker · Paras Singla · Apr 17, 2026

  199. A proposed consent log for A2A and MCP records the terms an agent accepted, but the agent fills it in itself

    Paper · · arXiv · Ravi Kiran Kadaboina · Apr 16, 2026

  200. An agent certificate draft ties access to a trust score set by the issuing CA, usually the agent operator's own

    Draft · · IETF Datatracker · Raza Sharif, CyberSecAI · Apr 10, 2026

  201. AITH claims 4.7 million agent checks a second, but the test simulated its post-quantum signatures

    Paper · · arXiv · Zhaoliang Chen · Apr 9, 2026

  202. An OAuth draft for AI agents' step-up login finishes the one-time-code path but leaves passkeys unfinished

    Draft · · IETF Datatracker · Martin Besozzi · Apr 3, 2026

  203. The commonest credential leak in AI agent skills is a debug print the framework hands to the model

    Paper · · arXiv · Zhihao Chen et al. · Apr 3, 2026

  204. Microsoft and Google made AI agent identity generally available in April; Okta's notes put its GA in May

    Release tracker · · 8 vendors' release notes · Apr 2026

  205. OpenID agent-claims draft adds a provider-set user, application or agent label; scores stay each provider's own

    Draft · · IETF Datatracker · Raza Sharif, CyberSecAI · Mar 26, 2026

  206. An agent-credential draft carries a hash of the user's instruction that its own verification steps never check

    Draft · · IETF Datatracker · Chudah Yakung, Attest · Mar 26, 2026

  207. AIP puts an agent's delegation chain in the token; its perfect score against attacks tests rules only AIP has

    Paper · · arXiv · Sunil Prakash · Mar 25, 2026

  208. A KubeCon demo moves MCP servers' OAuth checks into a gateway, safe only if nothing can reach a server directly

    Video · · CNCF [Cloud Native Computing Foundation] · Uploaded March 24, 2026

  209. Checking each agent call against the user's own task stopped all 634 off-task calls the authors wrote

    Paper · · arXiv · Reshabh K Sharma et al. · Mar 17, 2026

  210. An agent identity draft signs every tool call, but never finished saying whom the agent answers to

    Draft · · IETF Datatracker · James Cao et al. · Mar 16, 2026

  211. A cross-domain agent trust draft requires the call chain, then leaves its format to a version that never came

    Draft · · IETF Datatracker · Daniel King et al. · Mar 15, 2026

  212. An MCP signing draft shows a client who wrote a tool, and admits a poisoned tool can still be validly signed

    Draft · · IETF Datatracker · Raza Sharif, CyberSecAI · Mar 14, 2026

  213. Auth0's guide ties sessions to TLS fingerprints, including JA3, which Chrome changes on each new connection

    Article · · Auth0 Blog · Antonio Ortells · Mar 5, 2026

  214. OAuth 2.1's October draft bans plain PKCE and adds browser-app rules; 2.1-only clients can fail on older servers

    Draft · · IETF Datatracker · Dick Hardt et al. · Mar 2, 2026

  215. An OAuth client brokering many tools, as agent services do, can let a rogue tool take over a user's other tools

    Draft · · IETF Datatracker · Tim Würtele et al. · Mar 2, 2026

  216. A Huawei agent draft keeps one 'master agent' as gatekeeper and drops the line that had servers re-check it

    Draft · · IETF Datatracker · Yuan Ni et al. · Feb 28, 2026

  217. OAuth's in-app login draft lets a native app collect the password itself, and leaves each server to vet the app

    Draft · · IETF Datatracker · Aaron Parecki et al. · Feb 28, 2026

  218. An Alibaba and Cisco draft signs what the user was shown, then enforces a policy the agent wrote

    Draft · · IETF Datatracker · Dapeng Liu et al. · Feb 28, 2026

  219. An OAuth draft caps every refresh token at the user's grant, and tells the app when that grant ends

    Draft · · IETF Datatracker · Nick Watson, Google · Feb 27, 2026

  220. Auth0's Go JWT middleware v3 adds DPoP but accepts a reused proof for five minutes, and bearer tokens by default

    Article · · Auth0 Blog · Kunal Dawar · Feb 27, 2026

  221. OpenPort holds agent writes as drafts for an operator by default; its own tests check less than its spec asks

    Paper · · arXiv · Genliang Zhu et al. · Feb 22, 2026

  222. Google DeepMind wants agent authority to narrow at every hand-off, and misreads MCP's scopes on the way

    Paper · · arXiv · Nenad Tomašev et al. · Feb 12, 2026

  223. MACAW Security's trust layer signs every agent call, but what stopped its prompt-injection test was a policy

    Paper · · arXiv · Mohan Rajagopalan et al. · Feb 11, 2026

  224. Auth0's AgentCore guide says prompts alone are not enough, then lets the prompt decide when to ask a person

    Article · · Auth0 Blog · Kapil Patil · Feb 10, 2026

  225. An open spec for stopping agent actions before they run needs the vendor's help to cover ChatGPT or Copilot

    Paper · · arXiv · Herman Errico · Feb 10, 2026

  226. A Cisco-led agent draft puts the verifiable credential at a public URL, with selective disclosure a SHOULD it does not yet show

    Draft · · IETF Datatracker · Jean Diaconu et al. · Feb 6, 2026

  227. eBay researchers say AP2 does not make a payment mandate single-use, so they built a gateway that does

    Paper · · arXiv · Qianlong Lan et al. · Feb 6, 2026

  228. A China Mobile draft would end an agent's token when its task ends, if a webhook says so

    Draft · · IETF Datatracker · Meiling Chen et al. · Feb 4, 2026

  229. A secure-MCP proposal registers every agent and tool centrally, and never mentions MCP's own OAuth rules

    Paper · · arXiv · Xinyi Hou et al. · Feb 1, 2026

  230. In February Okta let AI agents reach its management APIs over MCP; Cloudflare added controls on MCP connections

    Release tracker · · 7 vendors' release notes · Feb 2026

  231. Faramesh holds each agent action for a signed permit; its bypass tests assume no path around the gate

    Paper · · arXiv · Amjad Fatmi · Jan 25, 2026

  232. Rubrik ties agent recovery to protected backups and puts identity oversight in Agent Cloud

    Podcast · · AI Security Podcast · Why AI Agents Fail in Production: Governance, Trust & The "Undo" Button · Jan 23, 2026

  233. OAuth's cross-device guidance ranks FIDO first, then CIBA backchannel login, and the device-code flow last

    Draft · · IETF Datatracker · Pieter Kasselman et al. · Jan 23, 2026

  234. Raut's January draft put AI agents in two new transaction-token claims; by April he used OAuth's act and sub

    Draft · · IETF Datatracker · Ashay Raut · Jan 20, 2026

  235. The draft replacing RFC 8725 requires rejecting malformed JWTs but only recommends denial-of-service limits

    Draft · · IETF datatracker · Yaron Sheffer et al. · Jan 12, 2026

  236. Cisco Duo's MCP beta lets agents register themselves; Duo calls client ID metadata documents the future

    Article · · Cisco Duo · Colin Medfisch · Jan 7, 2026

  237. In January Okta's agent product was in early access; Auth0 and Microsoft made machine-to-machine features GA

    Release tracker · · 7 vendors' release notes · Jan 2026

  238. A Shenzhen paper ties each AI agent to a verified owner and its exact code, at 15 to 40 seconds of proving a step

    Paper · · arXiv · Zibin Lin et al. · Dec 19, 2025

  239. One shared MCP token makes a whole company one identity in the logs; this paper wants per-user OAuth at a gateway

    Paper · · arXiv · Herman Errico et al. · Nov 25, 2025

  240. CORAL's public agent server rejected forged messages but let a wrong key open the session stream

    Paper · · arXiv · Yedidel Louck et al. · Nov 5, 2025

  241. Auth0's case for Token Vault: take the user ID out of the token call and let the session prove whose token it is

    Article · · Auth0 Blog · Abhishek Hingnikar, Okta · Nov 4, 2025

  242. On its authors' tasks, an LLM check of agent scopes works at one tool and refuses most valid three-tool requests

    Paper · · arXiv · Majed El Helou et al. · Oct 30, 2025

  243. AAGATE maps NIST's AI risk framework onto Kubernetes, and its paper never times the 'millisecond kill switch'

    Paper · · arXiv · Ken Huang et al. · Oct 29, 2025

  244. An MCP sandbox blocked every test attack that reached for the host; a poisoned tool that only redirected the agent got through

    Paper · · arXiv · Christoph Bühler et al. · Oct 24, 2025

  245. Huawei-led OAuth draft lets clients chain narrower tokens offline but leaves revocation delivery out of scope

    Draft · · IETF Datatracker · Li Ruochen et al. · Oct 20, 2025

  246. Rosenberg and White's AAuth now has the resource server, not the agent, write and sign the approval text

    Draft · · IETF Datatracker · Jonathan Rosenberg et al. · Oct 20, 2025

  247. An agent OAuth proposal has the helper forward grants before receiving access tokens

    Draft · · IETF Datatracker · Kehan Yao, China Mobile · Oct 20, 2025

  248. A Huawei draft fits A2A tasks into transaction tokens but no field says which agent is calling

    Draft · · IETF Datatracker · Peter Chunchi Liu et al. · Oct 20, 2025

  249. WIMSE leaves its application proof choice open, with different integrity coverage

    Draft · · IETF Datatracker · Brian Campbell et al. · Oct 16, 2025

  250. An October SCIM draft gives agents their own records, with security still unfinished

    Draft · · IETF Datatracker · Macy Abbey et al. · Oct 11, 2025

  251. An MCP threat survey shows agents trusting tool names and descriptions, and skips the spec's own OAuth rules

    Paper · · arXiv · Xinyi Hou et al. · Oct 7, 2025

  252. SPIFFE can authenticate an OAuth client; trust and registration still come first

    Draft · · IETF Datatracker · Arndt Schwenkschuster et al. · Oct 3, 2025

  253. RFC 9864 deprecates ambiguous signature identifiers without prohibiting their use

    Article · · IETF / RFC Editor · Michael B. Jones et al. · Oct 1, 2025

  254. Salesloft says the Drift intruder was in its GitHub account months before the Salesforce data theft

    Article · · Salesloft Trust Center · Sep 30, 2025

  255. One author's OpenID Connect for Agents proposal checks each delegation hop but makes the chain optional

    Paper · · arXiv · Subramanya Nagabhushanaradhya · Sep 30, 2025

  256. Stytch sells a one-call check for whether a visitor is an AI agent, priced at half a cent a lookup

    Podcast · · So What About AI Agents · EP 39 - Agentic Authentication | Bobbie Chen · Sep 23, 2025

  257. Agentic JWT binds an agent's token to its task and its own code, but it is one author's draft, not a standard

    Paper · · arXiv (cs.CR preprint 2509.13597) · Abhishek Goswami · Sep 16, 2025

  258. OpenID's credential issuance standard is OAuth for wallets, and assumes a trusted wallet is an app on a phone

    Article · · OpenID Foundation · Torsten Lodderstedt et al. · Sep 16, 2025

  259. Salesloft's store of customers' OAuth tokens was stolen, and Risky Business sees few fixes customers control

    Podcast · · Risky Business · Risky Business #805 -- On the Salesloft Drift breach and "OAuth soup" · Sep 3, 2025

  260. A stolen Drift credential opened Cloudflare's support cases, which held 104 Cloudflare API tokens

    Article · · Cloudflare Blog · Sourov Zaman et al. · Sep 2, 2025

  261. Under Shared Signals 1.0 a sender may accept a subscription and send nothing, so agent revocation needs a backup

    Article · · OpenID Foundation · Atul Tulshibagwale et al. · Aug 29, 2025

  262. GTIG traced Salesforce data theft to compromised Salesloft Drift tokens, then widened the scope to Workspace mail

    Article · · Google Cloud Blog (Google Threat Intelligence Group) · Austin Larsen et al. · Aug 26, 2025

  263. A WSO2 draft puts the AI agent in OAuth consent and the access token, but not how the agent gets its credential

    Draft · · IETF Datatracker · Thilina Shashimal Senarath et al. · Aug 26, 2025

  264. Auth0's DPoP explainer leaves out the access-token hash that RFC 9449 requires on every API call

    Article · · Auth0 Blog · Andrea Chiarelli · Aug 25, 2025

  265. Formal proofs find no new flaws in OpenID4VP over the Digital Credentials API, for a March 2025 draft

    Article · · OpenID Foundation · Fabian Hauck et al. · Aug 20, 2025

  266. A poisoned MCP tool got an agent to copy the client's config file without asking; deleting a file did ask

    Paper · · arXiv · Yongjian Guo et al. · Aug 18, 2025

  267. In a test harness, two of three MCP hosts refused a prompt asking for credentials; none refused a poisoned tool

    Paper · · arXiv · Yixuan Yang et al. · Aug 17, 2025

  268. A 'provable' bound on agent-memory injection assumes independent layers and fills in none of its detection rates

    Paper · · arXiv · Ken Huang et al. · Aug 17, 2025

  269. MCP-Guard's classifier alone came within half a point of its best full pipelines' F1 on the authors' test set, and ran faster

    Paper · · arXiv · Wenpeng Xing et al. · Aug 14, 2025

  270. A Tsinghua blockchain design for AI agents backs its defense claims with a table and reports no attack run

    Paper · · arXiv · Zhenhua Zou et al. · Aug 2, 2025

  271. An OAuth client that never registers: the July 2025 draft makes its URL the identity and leaves most server checks as SHOULDs

    Draft · · IETF Datatracker · Aaron Parecki et al. · Jul 23, 2025

  272. OpenID4VP 1.0 makes verifiers re-check what a wallet returns, and cannot show a holder acting for someone else

    Article · · OpenID Foundation · Oliver Terbu et al. · Jul 9, 2025

  273. An MCP privilege study says obscure servers are riskier; its own table points the other way

    Paper · · arXiv · Zhihao Li et al. · Jul 5, 2025

  274. A July OAuth draft proposes authorization for models inside a client

    Draft · · IETF Datatracker · Yurong Song et al. · Jul 3, 2025

  275. The July 2025 Cross App Access draft lets the IdP decide app-to-app access and treats agents as plain clients

    Draft · · IETF Datatracker · Aaron Parecki et al. · Jul 2, 2025

  276. A survey of MCP and A2A attacks pairs each identity threat with a fix, and tests none of them

    Paper · · arXiv · Mohamed Amine Ferrag et al. · Jun 29, 2025

  277. AI governance researchers argue OAuth tokens can't link an agent's work across services or sub-agents

    Paper · · arXiv · Alan Chan et al. · Jun 19, 2025

  278. MCP's June 2025 authorization spec: a server accepts only tokens issued for it and passes none upstream

    Article · · Model Context Protocol project · Jun 18, 2025

  279. ETDI would sign MCP tool definitions against lookalikes, but leaves open who vouches for the publisher's key

    Paper · · arXiv · Manish Bhatt et al. · Jun 2, 2025

  280. In Microsoft's agent tests, label checks blocked policy-breaking tool calls and its FIDES planner finished more tasks

    Paper · · arXiv · Manuel Costa et al. · May 29, 2025

  281. A Cloud Security Alliance paper wants AI agents on a new identity stack, with OAuth kept for simple cases

    Paper · · arXiv (cs.CR preprint 2505.19301) / Cloud Security Alliance · Ken Huang et al. · May 25, 2025

  282. The first Agent Name Service paper puts capabilities in the name and leaves protocol translation and governance out

    Paper · · arXiv (cs.CR preprint 2505.10609) / OWASP Agentic Security Initiative · Ken Huang et al. · May 15, 2025

  283. Germany's wallet builders say the state certifies and lists wallets, and users pick any listed one, Google's too if it meets the rules

    Podcast · · Identity at the Center · #354 - Kristina Yasuda & Torsten Lodderstedt on the EUDI Wallet and its Global Impact · First aired May 7, 2025 · Jun 9, 2025

  284. An MCP gateway can do OAuth for servers that have none; this one passes them a user header

    Paper · · arXiv · Ivo Brett · Apr 28, 2025

  285. A 'zero trust' registry against AI tool squatting still has to trust its administrator

    Paper · · arXiv · Vineeth Sai Narajala et al. · Apr 28, 2025

  286. An A2A threat model flags the Agent Card as an attack path, and its example flow never passes on the user's identity

    Paper · · arXiv · Idan Habler et al. · Apr 23, 2025

  287. OWASP's multi-agent threat guide finds the hop where a user's permission check drops out, but names no fix

    Article · · OWASP GenAI Security Project · OWASP Agentic Security Initiative · Apr 22, 2025

  288. MCP Guardian wraps tool calls in token and regex checks, leaving poisoned servers and agent IDs open

    Paper · · arXiv · Sonu Kumar et al. · Apr 17, 2025

  289. Most of Progent's protection from prompt injection comes from a policy written before the agent reads anything

    Paper · · arXiv · Tianneng Shi et al. · Apr 16, 2025

  290. An early MCP security checklist was never tested, and the protocol has since adopted only part of it

    Paper · · arXiv · Vineeth Sai Narajala et al. · Apr 11, 2025

  291. A rogue OAuth server can collect a client's signed assertion and replay it at an honest server the client also uses

    Article · · IACR Cryptology ePrint Archive · Pedram Hosseyni et al. · Apr 7, 2025

  292. RFC 9728 tells clients where an API's tokens come from and leaves most of the trust decision to them

    Article · · RFC Editor · Michael B. Jones et al. · Apr 2025

  293. Splitting an agent's privileges stopped every tested prompt injection, if users refuse each alert

    Paper · · arXiv · Juhee Kim et al. · Mar 17, 2025

  294. FAPI 2.0 issues only sender-constrained access tokens and leaves public clients out

    Article · · OpenID Foundation · Daniel Fett et al. · Feb 22, 2025

  295. Testing AI agents one at a time misses attacks that combine them, a Cooperative AI Foundation report argues

    Paper · · arXiv · Lewis Hammond · Feb 19, 2025

  296. An MIT-led paper has the user sign the agent's delegation token and lets OpenID Connect vouch for both parties

    Paper · · arXiv · Tobin South et al. · Jan 16, 2025

  297. RFC 9700 bans OAuth's password grant and loose redirect matching; binding access tokens stays a SHOULD

    Article · · IETF (RFC Editor) · Torsten Lodderstedt et al. · Jan 2025

  298. RFC 9679 lets a CBOR token name its holder's key by thumbprint alone, and leaves finding the key to the verifier

    Article · · RFC Editor · Kohei Isobe et al. · Dec 20, 2024

  299. In GNAP (RFC 9635), a client is known by its key, and tokens stay key-bound unless the server flags them bearer

    Article · · RFC Editor · Justin Richer et al. · Oct 1, 2024

  300. In May 2023, Parecki described OAuth 2.1 as consolidation and DPoP as token protection

    Video · · Identiverse - A CRA Resource · Jun 17, 2024

  301. The 2024 'IDs for AI' paper puts the ID on a chat session, not a model, and leaves trust in its issuer to others

    Paper · · arXiv · Alan Chan et al. · Jun 17, 2024

  302. OpenID Connect Core says only issuer plus subject identify a user; email must never be the key

    Article · · OpenID Foundation · Nat Sakimura et al. · Dec 15, 2023

  303. RFC 9470 lets an API demand a fresher or stronger sign-in, with no shared scale for 'stronger'

    Article · · RFC Editor · Vittorio Bertocci et al. · Sep 8, 2023

  304. DPoP token binding depends on checks at the resource server

    Article · · RFC Editor · Daniel Fett et al. · Sep 2023

  305. Rich Authorization Requests need API-specific permission rules

    Article · · RFC Editor · Torsten Lodderstedt et al. · May 1, 2023

  306. RFC 9207 has OAuth servers name themselves in each response; clients must refuse a missing name only where they expect one

    Article · · RFC Editor · Karsten Meyer zu Selhausen et al. · Mar 1, 2022

  307. RFC 9068 makes resource servers check a JWT access token's type and audience, and warns a client could pose as a user

    Article · · RFC Editor · Vittorio Bertocci, Okta · Oct 1, 2021

  308. CIBA's human-approval step carries a short matching code, not a description of the action

    Article · · OpenID Foundation · Gonzalo Fernandez Rodriguez et al. · Sep 1, 2021

  309. Signed OAuth requests can be bypassed until the server refuses unsigned ones, and RFC 9101 leaves that off by default

    Article · · RFC Editor · Nat Sakimura et al. · Aug 1, 2021

  310. RFC 8705 lets OAuth bind tokens to a client certificate, and leaves the proxy in front of the API to the deployer

    Article · · RFC Editor · Brian Campbell et al. · Feb 28, 2020

  311. A 2020 simulation fit the web's certificate revocations in under 5 MB; OAuth's Token Status List draft cites it

    Article · · NDSS Symposium 2020 · Trevor Smith et al. · Feb 12, 2020

  312. OAuth's resource indicators RFC says servers should bind tokens to a resource, but requires it of neither side

    Article · · RFC Editor · Brian Campbell et al. · Feb 1, 2020

  313. RFC 8725: the caller, not the JWT header, picks the algorithm, and "none" is discouraged, not banned

    Article · · RFC Editor · Yaron Sheffer et al. · Feb 2020

  314. The token exchange RFC that agent designs cite says its record of earlier actors is not for access decisions

    Article · · IETF Datatracker · Michael B. Jones et al. · Jan 1, 2020

  315. The OAuth device grant names remote phishing as its risk and leaves the defence mostly to what the approval screen tells the user

    Article · · RFC Editor · William Denniss et al. · Aug 1, 2019

  316. In draft FAPI, token binding did not make phished tokens useless: the attacker had the bound client spend them

    Paper · · arXiv · Daniel Fett et al. · Jan 31, 2019

  317. RFC 8485 makes assurance values meaningful only within a named trust framework

    Article · · RFC Editor · Justin Richer et al. · Oct 12, 2018

  318. Under RFC 8417 a security event token reports a fact, not an order, and the receiver decides what to do

    Article · · RFC Editor · Phil Hunt et al. · Jul 2018

  319. RFC 8414 tells an OAuth client to discard server metadata whose issuer differs from the URL it started from

    Article · · RFC Editor · Michael B. Jones et al. · Jun 1, 2018

  320. CWT leaves required claims to the application, including issuer, audience and expiry

    Article · · RFC Editor / IETF · Michael B. Jones et al. · May 1, 2018

  321. RFC 8252 puts native-app OAuth authorization outside the host app’s browser control

    Article · · IETF / RFC Editor · William Denniss et al. · Oct 1, 2017

  322. RFC 8176 reports authentication methods separately from assurance classes

    Article · · IETF / RFC Editor · Michael B. Jones et al. · Jun 1, 2017

  323. A 2017 security proof for OpenID Connect assumes fixes the spec did not yet require

    Paper · · arXiv · Daniel Fett et al. · Apr 27, 2017

  324. Trying to prove OAuth 2.0 secure, a 2016 Trier paper found four attacks, the IdP mix-up among them

    Paper · · arXiv · Daniel Fett et al. · Jan 6, 2016

  325. SCIM leaves the meaning of active status and group access to each provider

    Article · · RFC Editor / IETF · Phil Hunt et al. · Sep 1, 2015

  326. RFC 7644 leaves SCIM's access rules to each deployment, and a bulk request can succeed in part

    Article · · RFC Editor · Phil Hunt et al. · Sep 1, 2015

  327. PKCE's 2015 standard let servers accept clients that skip it and treated an omitted method as the weaker plain

    Article · · RFC Editor · Nat Sakimura et al. · Sep 2015

  328. In 2015, OpenID Connect discovery let an attacker's server choose where a client sent the user's code

    Paper · · arXiv · Christian Mainka et al. · Aug 18, 2015

  329. RFC 7592 defines replacement updates for managed OAuth registrations

    Article · · RFC Editor · Justin Richer et al. · Jul 9, 2015

  330. RFC 7591 asks OAuth servers to accept clients with no token, and calls their signed statements self-asserted

    Article · · RFC Editor · Justin Richer et al. · Jul 9, 2015

  331. RFC 7522 lets a SAML assertion serve as a grant or authenticate the client independently

    Article · · IETF / RFC Editor · Brian Campbell et al. · May 1, 2015

  332. OAuth's assertion framework is built for bearer assertions, and one can buy fresh tokens until it expires

    Article · · RFC Editor · B. Campbell et al. · May 1, 2015

  333. RFC 7519 makes "none" mandatory to implement and leaves refusing an unwanted algorithm as a SHOULD

    Article · · RFC Editor · Michael B. Jones et al. · May 1, 2015

  334. RFC 7523 lets a signed JWT authenticate an OAuth client or serve as a grant, and leaves replay checks optional

    Article · · RFC Editor · Michael B. Jones et al. · May 1, 2015

  335. Macaroons, 2014: bearer tokens any holder can narrow but not widen, checkable only by the service that minted them

    Article · · NDSS Symposium 2014 (Google Research) · Arnar Birgisson et al. · Feb 23, 2014

  336. RFC 7009 requires refresh-token revocation but only recommends it for access tokens, which may outlive a revoke

    Article · · RFC Editor · Torsten Lodderstedt et al. · Aug 1, 2013

  337. RFC 6819 warned in 2013 that servers receiving a token may reuse it, and offered audience binding and client-bound tokens

    Article · · RFC Editor · T. Lodderstedt et al. · Jan 2013

  338. RFC 6750 tokens work for whoever holds them; RFC 9700 now urges key binding and bars them from query strings

    Article · · RFC Editor · Michael B. Jones et al. · Oct 1, 2012

  339. RFC 6749 admits a server can't tell who presents a token; the fixes arrived in 2020 and 2023

    Article · · RFC Editor · D. Hardt et al. · Oct 2012

  340. Richer's 2023 draft let each service in a call chain add a hash-linked token, but left serialization unfinished

    Draft · · IETF (individual Internet-Draft) · Justin Richer · Sep 15, 2023

  341. A 2025 workload identity draft kept credential exchange for crossing trust domains, and never to gain more trust

    Draft · · IETF Datatracker · Arndt Schwenkschuster, Defakto · Mar 3, 2025

  342. Microsoft's 2023 keynote: workload standards should carry identity across service calls first, policy later

    Video · · Identiverse - A CRA Resource · Recorded May 31, 2023 · Uploaded June 17, 2024

  343. Ian Glazer's sketch of a 2025 IAM stack: one shared identity data layer, with Shared Signals announcing changes

    Podcast · · Identity at the Center · #325 - Theorycrafting Modern Identity Architecture with Ian Glazer · Jan 13, 2025

In our columns

  1. Narrowing agent hand-offs protects little while one agent's role reaches all the others

    Column · Nov 11, 2026

  2. An agent's log must name whom it acted for, and the agent must not be the one writing it

    Column · Nov 9, 2026

  3. Third-party tokens need a check on every use; the vendor's breach notice comes days late

    Column · Nov 8, 2026

  4. A signed AI agent name is an IP address with a key, not a login

    Column · Oct 30, 2026

  5. Give each AI agent its own identity, or its kill switch will stop a person

    Column · Oct 23, 2026

Related terms

What appears alongside OAuth in the same briefings.

Model Context ProtocolTransaction TokensFIDO2 / passkeysOAuth Identity and Authorization Chaining Across DomainsAAuth (Hardt)Identity Assertion Authorization GrantOpenID Connect Core 1.0Backend for Frontend

Was this explainer useful?

Share this explainer

Pass it on. Every claim has a permanent number, so what you share today still points at the same words next year.