caveman
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for persona modification and response formatting.
- [SAFE]: No external dependencies, scripts, or network requests are defined.
- [SAFE]: The skill includes explicit 'Auto-Clarity Exceptions' which instruct the agent to drop the persona for security warnings and irreversible actions, demonstrating a security-conscious design.
Audit Metadata