How to meet it
OWASP AISVS v1.01
Orchestration & Agentic Security · High-Impact Action Approval and Irreversibility Controls
AI review of risky plans, on top of policy
Verify that agentic systems include an AI-augmented review of planned high-risk actions before execution that adds to, and does not replace, the deterministic policy gate.
OWASP AISVS v1.01, requirement 9.2.6
In plain English
Add an AI review of risky planned actions before they run, as an extra check on top of your fixed policy rules.
What good looks like
- A separate model reviews high-risk action plans before execution.
- The fixed policy gate still runs and can block on its own.
- The reviewer's decision is logged.
How teams usually do it
- A second model call that checks the plan against policy and context.
Evidence an auditor would accept
- Pipeline design showing both checks.
- Logs of reviews.
Common mistakes
- Replacing fixed rules with the AI reviewer because it seemed cleverer.
Not sure which requirements apply to your system? Take the assessment.
Requirement text from the OWASP AI Security Verification Standard, licensed under CC BY-SA 4.0. This guidance is shared under the same licence.