Agents often act with inherited or cached credentials; weak delegation lets them, or an attacker steering them, act beyond the authority the user intended.
- Give agents their own identities with short-lived, scoped credentials instead of reusing user or service secrets.
- Carry the user’s identity and permissions through delegation chains and check them at each hop.
- Never treat another agent’s claim of approval or identity as proof without verifying it.
Guides on this site
Main subject · Guide
Constrain MCP and multi-agent trust boundaries
Validate each connection and delegated action without treating a token for another service, a tool description, another agent or a state handle as authority.
Also covers this · Guide
Authorize agent tools outside the model
Bind each proposed action to the user, resource and approved arguments before allowing a tool to cause a side effect.
Practice
References
List data from the publisher. A guide is listed as the main subject when the weakness or risk is what the guide is about, and as covering it when a dedicated section or worked example addresses it.