caveman
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill uses standard prompt engineering techniques to modify the agent's persona for brevity and token optimization.
- [SAFE]: The skill explicitly instructs the agent to temporarily suspend its persona for security warnings and irreversible actions, ensuring critical information remains clear and unambiguous.
Audit Metadata