caveman
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a persistent persona and output formatting rules intended to override the agent's default communication style. This behavior is documented as the skill's primary purpose and does not attempt to bypass core safety filters or extract system prompts.
- [SAFE]: The instructions explicitly maintain standard clarity for security warnings and destructive operations, demonstrating a design that respects safety protocols. No external network requests, sensitive file access, or suspicious code patterns were found.
Audit Metadata