Skip to content
IAM Insights

Explainers · Glossary

Scope attenuation

attenuation of scope · recursive delegation · offline attenuation

Narrowing the permissions at every hand-off, so a sub-agent that receives a task gets only what that task needs rather than everything its parent held.

In our briefings

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

  1. The paper's central claim is that every agent identity mechanism it surveyed proves which container is acting and nothing about what the agent intends. A trusted execution environment, a zero-knowledge proof or a signed credential can all verify while the model inside has been hijacked by a prompt injection, so the authors propose treating identity as a continuously updated confidence that joins what an agent declared with what it was observed doing. They argue it from a worked example, not a measurement; the TU Berlin prototype of agents with DIDs supplies one, a handshake whose credentials checked out while both agents agreed to skip a step their instructions required.

    A survey rates only workload identity ready for agents, and argues no standard can tell what an agent intendsBI-FIND-2026-0644

  2. The OpenID Foundation's own community group draws the line on what today's identity standards do for AI agents: they 'can work for synchronous agents using multiple tools across a single trust domain, but not asynchronous or multi-domain contexts.' In plain terms, OAuth 2.1 handles an agent that works inside one organization while its user is present. It falls short when the agent runs unattended, crosses into another organization's systems, or acts for several people at once. Everything vendors now sell as agent identity for the simple case rests on standards that already existed; the hard cases have drafts and proposals.

    OAuth handles an agent in one company, working while you watch. The OpenID paper says that is where it stops.BI-FIND-2025-0054

  3. The co-chair of the OpenID Foundation's AI identity group does not think agents need a new identity system. Tobin South's position is that web login, SAML, SCIM and the identity provider's handling of agents each need a modest upgrade, that no single fix exists, and that anyone who says otherwise is selling a product. He points out that identity providers already let a company declare an agent, tie it to a person and switch it off. The IETF's agent-authentication draft opens with the same complaint, that the field keeps reinventing mechanisms it already has.

    An OpenID Foundation co-chair says AI agents need modest upgrades to today's identity systems, not a new oneBI-FIND-2025-0088

Cited in 4 briefings

Every briefing that discusses this term, newest first.

  1. 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

  2. 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

  3. 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

  4. 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