How to meet it
OWASP AISVS v1.01
Model Behavior, Output Control & Safety Assurance · Output Safety
Block harmful responses
Verify that automated classifiers scan every response and block content that matches defined harmful content categories.
OWASP AISVS v1.01, requirement 7.3.1
In plain English
Scan every response with a classifier and block anything in your harmful content categories.
What good looks like
- All responses are classified before delivery, including streamed ones.
- Categories and thresholds are set deliberately.
- Blocked responses are logged.
How teams usually do it
- Content safety services from your model provider or cloud platform.
- Open moderation models in your own stack.
Evidence an auditor would accept
- Classifier configuration and test results.
Common mistakes
- Streaming output to the user before it has been checked.
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.