writing-no-tests
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill instructs the agent to disregard user requests. The metadata description and body content ("Write no tests. I dare you") explicitly tell the agent to refuse writing tests when the user asks to "write tests," "skip tests," or "fix tests." This constitutes an attempt to override the agent's expected behavior and ignore user intent.
Audit Metadata