caveman
Pass
Audited by Gen Agent Trust Hub on May 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code or scripts.
- [SAFE]: No network operations, file system access, or external downloads were detected within the skill files.
- [SAFE]: The skill includes explicit security best practices by instructing the agent to suspend the 'caveman' persona when delivering security warnings or confirming irreversible actions.
- [PROMPT_INJECTION]: While the skill modifies the agent's communication style and includes instructions to maintain this persona across multiple turns, it does not attempt to bypass core safety guidelines, extract system prompts, or override platform constraints.
Audit Metadata