caveman
Pass
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions intended to modify the AI's persona and response style. There are no executable scripts, shell commands, or external dependencies.
- [SAFE]: The instructions include a specific 'Clarity exception' that directs the agent to drop the persona for security warnings and confirmation of irreversible actions, which is a defensive best practice for persona-based prompts.
Audit Metadata