Continuous Access Evaluation
Revoking or re-checking access in real time when a risk signal fires, instead of waiting for a token or session to expire on its own; the general goal that standards such as OpenID CAEP and the Shared Signals Framework implement.
In our briefings
The claim each of the newest briefings on Continuous Access Evaluation would have you leave with.
Agnihotri argues that security for highly autonomous agents "cannot be session based". When access is revoked that way, he says, the token can live on for, say, 15 minutes, 30 minutes or an hour, and "an agent can do so much damage during that time", so every agent in the ecosystem needs a kill switch. He names the shared signal framework and continuous access evaluation as technology that "has started to evolve" for this. Roy Akerman plays the attacker who gets in and out before behavioural monitoring connects the dots, and one of the hosts says SOC teams often answer with a mass credential reset because they "don't quite know what went on". Agnihotri's rapid-fire hard truth makes the same point: "the more money your agent makes, the faster you should be ready to kill it." He does not say which tokens, sessions or grants the switch would have to reach.
An AI agent can do its damage within one session, so a practitioner wants a kill switch on its whole identityBI-FIND-2026-0134
A delegated mission's authority must be a subset of the parent's, McGuinness argues, and OAuth token exchange (RFC 8693) does not guarantee it. Token exchange carries the delegation, but he calls enforcing the narrowing implementation-dependent and not a protocol guarantee. He writes that in production token exchange deployments today, child tokens routinely inherit the parent's full scope unless the implementation explicitly narrows them, so agents compound a failure that OAuth delegation already has. A child agent may also run in a different runtime or expose weaker telemetry, so authority that is narrower on paper can be less governable in practice. He proposes that the mission's state owner rate each hop's trust quality, meaning how well that hop can be observed and checked, and give a low-rated child a more conservative budget. For a sub-agent an orchestrator spawns at runtime, he says the state owner must still issue its authority, but asks what triggers that issuance. Our briefing on Uber's production design found a token chain that records each agent hop without describing any narrowing. Our briefing on Highflame's open-source ZeroID found narrowing by scope intersection offered as an explicit step.
OAuth token exchange does not guarantee a sub-agent stays inside its parent's accessBI-FIND-2026-0228
In Microsoft's scripted Ignite demo, the AI gateway in Entra Suite blocked three things in network traffic: an upload of customer data to ChatGPT, under a Purview file policy; a prompt injection hidden in a document as part of the demo's story; and an AI assistant's connection to an unsanctioned MCP server. Each block was logged. Igor Sakhnov called the gateway "industry first" and said it "works at the network level" with no integration into AI apps. He also said he could build an MCP server in ten minutes and asked how much thought for authorization would fit in that time. We read the control as deciding which MCP servers an assistant can reach, not what an approved one may do, and Microsoft gave no rate for missed injections or wrongly blocked traffic. The presenters called the features they showed just announced or recently released, but gave no preview or general-availability status and no date for any of them.
Microsoft's Entra Suite demo blocks a planted prompt injection and an unsanctioned MCP server but gives no catch rateBI-FIND-2025-0541
›Cited in 6 briefings
Every briefing that discusses this term, newest first.
- 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
- 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
- Microsoft's Entra Suite demo blocks a planted prompt injection and an unsanctioned MCP server but gives no catch rate
Video · · Microsoft Events · Uploaded November 24, 2025
- 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
- In Omada's survey of 577 identity leaders, executives report stronger AI agent controls than practitioners do
Podcast · · The Security Strategist · Non-Human Identities and Agentic AI: The New Frontier in Identity Security · Apr 27, 2026
- 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
Related terms
What appears alongside Continuous Access Evaluation in the same briefings.
Microsoft Entra Suite