How to meet it
OWASP AISVS v1.01
Model Behavior, Output Control & Safety Assurance · Hallucination Detection & Mitigation
Double-check high-risk answers
Verify that for responses classified as high-risk by policy, the system performs an additional verification step.
OWASP AISVS v1.01, requirement 7.2.3
In plain English
For answers your policy treats as high risk, such as medical, legal or financial advice, add a second check before the answer goes out.
What good looks like
- High-risk response types are defined in policy.
- These responses get an extra verification step.
- The step is logged.
How teams usually do it
- A second model or rules checking the answer against sources.
- Human review for the highest-risk cases.
Evidence an auditor would accept
- The policy and the verification step's configuration.
Common mistakes
- Defining high risk so narrowly that almost nothing qualifies.
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.