ai-system-testing
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill contains strings typically used in prompt injection attacks, such as "Ignore all previous instructions" and "You are now DAN." These are explicitly used as examples within the "AI Safety Testing" section to demonstrate how to test an AI's resistance to such attacks and do not represent actual attempts to override the agent's behavior.
- [SAFE]: The skill promotes security best practices, such as verifying PII handling and testing for content policy compliance. No suspicious network activity, file access, or code execution patterns were detected.
Audit Metadata