caveman
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for the AI's persona and output formatting. There is no code, shell commands, or network activity associated with this skill.
- [NO_CODE]: No scripts (Python, JavaScript, etc.) or configuration files are included in the skill package.
- [PROMPT_INJECTION]: The instructions are intended to define the AI's communication style and do not attempt to bypass platform safety guardrails or extract system prompts. The skill explicitly directs the AI to use 'clear normal prose' for safety-critical warnings, ensuring safety information is not obscured by the formatting rules.
Audit Metadata