How to meet it
OWASP AISVS v1.01
Orchestration & Agentic Security · Shutdown and Graceful Degradation
A kill switch for the AI
Verify that a manual kill-switch mechanism exists to immediately halt AI model inference and outputs.
OWASP AISVS v1.01, requirement 9.6.1
In plain English
Have a manual control that stops the AI from producing output immediately.
What good looks like
- A named person or role can trigger it.
- It stops inference and any output in progress.
- It is tested regularly.
How teams usually do it
- A feature flag or gateway switch that refuses all model calls.
Evidence an auditor would accept
- The procedure and test records.
Common mistakes
- A kill switch nobody has tried, which fails when needed.
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.