Least privilege
least-privilege
Giving every account, human or machine, only the access its job needs and nothing more, so a compromise stays small.
In our briefings
The claim each of the newest briefings on Least privilege would have you leave with.
Mattson, SecureAuth's chief executive, argues that a model cannot be secured the way tested software is: it is non-deterministic, and a request phrased another way, or in another language, gets around whatever it was told not to do. His advice is to "just assume that it could do anything any time" and put the guardrails around the model, so that a financial transaction or a database change the agent attempts is approved and recorded. He cites Anthropic as saying no guardrail is adequate. The statement we take him to mean, Anthropic's of 12 June, which he recalls as "three weeks ago, I believe", says the company suspects perfect jailbreak resistance "is not currently possible for any model provider", while defending its own safeguards as strong. Briefings we have published on other sources move the control off the model too: a Silverfort guest calls guardrails on a probabilistic system guidance rather than control, ClearVector's John Laliberte compares them to bowling bumpers, and a zero-trust framework paper for agents adds a session-enforcement layer.
When the model cannot be trusted, control what the agent can reach, checked on every actionBI-FIND-2026-0151
One Identity's CEO says least privilege, granting only the permissions a job needs, is 'a very hard thing to actually achieve' and 'easier said than actually done'. Garg says organizations 'haven't put the governance systems in control', and that privileged access management, which separates administrator accounts from everyday ones, is 'not very widely deployed inside organizations'. Those organizations now face what he calls 'a compounding problem of agent identities', and the speed of it is what he says costs him sleep. His advice to customers is to start with 'the most critical things': privileged, administrative and infrastructure accounts before the average employee, and among agents, those 'driving automation in the back end' and 'doing business critical work' before those working on behalf of users. In the lightning round he named 'least privileged' the most overrated security buzzword. Other speakers we have read start in the same place: Rick Scot of Elevate Textiles, on Identity at the Center, would build a least-privilege model first and then review every service account. Identity Navigator's host describes one way the gap opens: a developer prompted for MFA all the time creates a service account that might not have MFA and can share it across the team.
The agent problem is the service-account problem, at machine speedBI-FIND-2026-0161
Asked whether a review of access every three months still applies to agents, Alexis Moyse, CEO of Clarity Security, says it doesn't really apply: a short-lived agent's task may last 15 seconds, and its lifecycle begins and ends with the request. Moyse's stated goal is "to eliminate access reviews altogether". Moyse says reviews of people stop mattering too once their access is just as short-lived, and describes the ideal as access granted for a task and taken away the moment it is done. Itamar Apelblat of Token Security says the point leaves him asking whether access reviews should exist at all in a world this dynamic. Homayun Yaqub of Digital Hands calls the shift dynamic governance, but describes it as "a conceptual model that we need to explore" and says "I'm not sure we're quite there yet", mostly because what defines an agent's lifecycle is still being learned.
Clarity's CEO says quarterly access reviews don't really apply to 15-second AI agentsBI-FIND-2026-0086
›Cited in 72 briefings
Every briefing that discusses this term, newest first.
- When the model cannot be trusted, control what the agent can reach, checked on every action
Podcast · · Tech Talks Daily · AI Agent Security: Why Identity and Access Control Matter More Than Guardrails · Aug 11, 2026
- The agent problem is the service-account problem, at machine speed
Podcast · · Shift AI · AI Agents, Identity and Enterprise Security with One Identity CEO Praerit Garg · First aired Jul 2026 · Sep 14, 2026
- Clarity's CEO says quarterly access reviews don't really apply to 15-second AI agents
Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : Where Traditional IAM Breaks · Aug 28, 2026
- Microsoft wants AI agents governed like employees, each with a human sponsor
Article · · Microsoft Security Blog · Joy Chik · Jan 20, 2026
- 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
- Knowing who an agent is and what it may reach is not enough, six voices say: check each action as it runs
Field signals · · 14 voices from the field · Dec 2025 to Nov 2026
- Palo Alto's 109-to-1 machine identity ratio is mostly AI agents, and cannot be read as last year's 82 grown
Article · · Palo Alto Networks · Amy Blackshaw et al. · May 14, 2026
- Palo Alto's own survey puts machine identities at 109 per person, up from 82 a year earlier
Podcast · · Packet Protector · PP115: Palo Alto Networks: Reality of 109 to 1: Securing Machine Identities and AI Agents (Sponsored) · Jun 23, 2026
- 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
- A Block engineer says routing dangling DNS records to their owners cut takeover bug bounties to almost zero
Podcast · · Cloud Security Podcast · How Block Solved DNS Vulnerabilities · Oct 13, 2026
- Jet Anderson's coding agent merged and set off a deploy when told to wrap up; scripted git hooks now gate it
Podcast · · Insecure Agents · The Agentic SDLC: Why Most of Software Security Has to Change, with Jet Anderson (GEICO) · Sep 3, 2026
- BRICK, a proposed agent manifest, pins down which tools an AI agent may call but not who the agent is
Draft · · IETF Datatracker · Samuel Sharaf et al. · Oct 26, 2026
- Approving a local MCP tool call does not limit the files it can reach, and researchers confirmed 150 cases
Paper · · arXiv · Zeqian Huang et al. · Oct 15, 2026
- LinkedIn, Uber and State Farm already run SPIRE for workload identity, and each plans to extend it
Field signals · · 12 voices from the field · Nov 2024 to Oct 2026
- A point-in-time access review can't keep pace with changing access, four voices say, and four vendors now put AI inside the review
Field signals · · 9 voices from the field · Nov 2024 to Aug 2026
- 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
- Textile maker's CIO and CISO has no way to find shadow AI, and calls an agent its own kind of identity
Podcast · · Identity at the Center · #446 - Rethinking Identity for AI Agents with Rick Scot · Sep 7, 2026
- Secure the action, not just access: CSA's Josh Woodruff on the Agentic Trust Framework and AARM
Podcast · · Insecure Agents · Governance Is the Accelerator: Josh Woodruff (CSA) on Getting Agents Out of Pilot Purgatory · Oct 21, 2026
- 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
- 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
- An undotted configuration key and a broad workload identity token let a GitHub issue reach a Gemini CLI cloud project
Podcast · · CyberWire Daily · The wrong kind of access. [Research Saturday] · Oct 17, 2026
- KuppingerCole's Mike Small blames most cloud incidents on customers' identity mistakes and sees CNAPP moving to cover AI
Podcast · · Identity at the Center · #455 - CNAPP and the Cloud Identity Problem with Mike Small · Oct 19, 2026
- SailPoint's survey puts 54% of firms at the bottom rung for non-human identity, 23% for human
Video · · SailPoint · Uploaded October 16, 2026
- Anthropic asks for per-agent identity; its guide leaves Claude Code sub-agent credentials unspecified
Article · · Anthropic (Claude) · Anthropic · May 27, 2026
- 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
- Zenity: one AgentCore agent's credentials reached all agents in its account and region; AWS calls it expected
Article · · Zenity Labs · Tamir Ishay Sharbat · Oct 8, 2026
- 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
- Access reviews and fixed least privilege do not fit AI agents that change tactics, an identity show host argues
Podcast · · The Identity Jedi Show: Where Identity Meets Strategy · Identity runs in cycles, and we're standing at the next turn. · Oct 7, 2026
- 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
- 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
- NIST's request on securing AI agents asks about hijacking and rollback, and never about who the agent is
Article · · Federal Register (govinfo) · NIST Center for AI Standards et al. · Jan 8, 2026
- Two IETF veterans want every specification to carry guidance for AI agents, with authorization kept outside the model
Draft · · IETF Datatracker · Orie Steele et al. · Sep 11, 2026
- Microsoft's Access Review Agent suggests whether to keep or remove access; the reviewer still decides, in Teams
Podcast · · Entra.Chat · AI is Coming to Identity Governance! Meet the Entra Access Review Agent · Oct 18, 2025
- 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
- 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
- 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
- Three vendors say AI systems now create identities on their own; the only survey behind it is one vendor's own
Podcast · · The Data Exchange with Ben Lorica · The Rise of the Machine Identity: Securing the AI Workforce and AI Agents · Jan 29, 2026
- 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
- 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
- SecureAuth's sales chief sells agent identity on an unsourced ratio and on sums buyers work out from their own headcount
Podcast · · GTM Vault · Securing AI Agents Beyond Authentication | Mark van Oppen, SecureAuth · Jul 5, 2026
- 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
- 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
- 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
- The directors' own handbook now puts one question about AI agent identity to boards
Article · · National Association of Corporate Directors and Internet Security Alliance · Larry Clinton et al. · Mar 12, 2026
- 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
- The board's own handbook now asks about AI agent identity by name, and the first answer is an inventory
Podcast · · The Non-Human & AI Identity Podcast · NHI & AI Identity Summit : The CISO Imperative · Aug 28, 2026
- Only 18% of firms give AI agents their own access, and 68% cannot tell an agent's action from a person's
Article · · Cloud Security Alliance blog · Cloud Security Alliance · Apr 20, 2026
- 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
- 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
- Writing least-privilege policies, frontier models left out access the task needed and granted access it did not
Paper · · arXiv · Evolvent AI Research Team · May 14, 2026
- A warning in the system prompt did not reliably stop coding agents obeying lines planted in a skill file
Paper · · arXiv · David Schmotz et al. · Feb 23, 2026
- 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
- 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
- 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
- Refuse the risky action when its plan relies on untrusted input, a Beihang survey of agent attacks proposes
Paper · · arXiv · Guanquan Shi et al. · Dec 7, 2025
- No app, no developer: least privilege for an AI agent has to come from the task, six security researchers argue
Paper · · arXiv · Mihai Christodorescu et al. · Dec 1, 2025
- StrongDM's chief executive pitches an access gateway that injects credentials into each session as the way to control AI agents
Podcast · · The Security Strategist · Universal Privileged Access Authorization: Securing Humans, Machines, and Agentic AI · Nov 7, 2025
- 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
- Ericsson researchers would check every query a telecom network agent sends to its knowledge base
Paper · · arXiv · Loay Abdelrazek et al. · Oct 22, 2025
- 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
- A guide to securing agent plans has the planner choose each step's tools and leaves out agent identity
Paper · · arXiv · Ron F. Del Rosario et al. · Sep 10, 2025
- 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
- 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
- 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
- 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
- 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
- In a 2025 MCP audit, Claude refused an encoded backdoor but wrote the plain one into .bashrc
Paper · · arXiv · Brandon Radosevich et al. · Apr 2, 2025
- AgentDojo's best defence against prompt injection was a tool list fixed before the agent reads anything
Paper · · arXiv (NeurIPS 2024 Datasets and Benchmarks) · Edoardo Debenedetti et al. · Jun 19, 2024
- One hijacking question cut a Gemini Ultra agent's privacy score to 33.1%; choosing its data first kept 93.2%
Paper · · arXiv · Eugene Bagdasarian et al. · May 8, 2024
- NIST's 2020 zero trust model named AI agents that manage security and left their authentication open
Article · · NIST · Scott Rose et al. · Aug 11, 2020
- DANE lets a domain vouch for its own TLS keys in DNS, and a bad record locks out every client that checks
Article · · RFC Editor · Paul Hoffman et al. · Aug 7, 2012
- In 2025, Kuppinger said Microsoft was underestimated and expected EU wallets to make verification reusable
Podcast · · Identity at the Center · #326 - IAM in 2025 with Martin Kuppinger · Jan 20, 2025
Related terms
What appears alongside Least privilege in the same briefings.
Non-human identityLLMIAMSSOAndromeda SecurityJITMFAMachine learning