How to meet it
OWASP AISVS v1.01
Orchestration & Agentic Security · High-Impact Action Approval and Irreversibility Controls
Enforce the reversibility rules
Verify that the agent runtime enforces reversibility classifications by blocking, requiring approval, or restricting actions based on their impact and ability to be reversed.
OWASP AISVS v1.01, requirement 9.2.4
In plain English
Apply the reversibility labels: let read-only actions through, add approval or limits for reversible ones, and block or tightly control irreversible ones.
What good looks like
- The runtime reads the class and applies a rule for each.
- Irreversible actions always need approval or are blocked.
- Rules cannot be changed by the agent.
How teams usually do it
- Policy rules in the tool gateway keyed on the reversibility class.
Evidence an auditor would accept
- Policy configuration and test results for each class.
Common mistakes
- Classifying actions but never using the classes.
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.