Skip to content
AI Agent Access Control

Write the agent's permission policy from what its tools actually call

Check 6 of 30: Write the agent's permission policy from what its tools actually call. Broad starter policies make every tool call possible, including ones nobody planned. A policy limited to the real calls limits what a wrong or hijacked call can do.

The whole checklist ยท The map

Why it matters

Broad starter policies make every tool call possible, including ones nobody planned. A policy limited to the real calls limits what a wrong or hijacked call can do.

How, in each cloud

AWS
Start from the documented minimum policy and narrow it; AWS says to use broad deployment permissions only for development and testing.
Google Cloud
Grant the agent identity only the roles its code needs; Google describes agent identity as enabling a least-privilege approach.
Azure
Grant the least privilege needed and avoid broader roles at broader scopes.

What the documentation says

  • "Use broad deployment permissions only for development and testing." (source)
  • "Agent identity provides a per-agent identity that enables a least-privilege" (source)
  • "When planning your access control strategy, it's a best practice to grant users the least privilege to get their work done." (source)

Sources

  1. docs.aws.amazon.com/bedrock-agentcore/latest/devguide/runtime-permissions.html, read 10 Nov 2026
  2. docs.cloud.google.com/gemini-enterprise-agent-platform/scale/runtime/agent-ident, read 10 Nov 2026
  3. learn.microsoft.com/en-us/azure/role-based-access-control/best-practices, read 10 Nov 2026

Last reviewed 16 Nov 2026.