caveman
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security threats detected. The skill focuses exclusively on modifying the AI's linguistic style to be more concise.
- [PROMPT_INJECTION]: No attempts to override system prompts or bypass safety filters were found. The 'caveman' mode is a formatting instruction triggered by explicit user request.
- [DATA_EXFILTRATION]: There are no network requests, file system access, or credential handling operations.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute any external scripts or packages.
- [INDIRECT_PROMPT_INJECTION]: While the skill instructions dictate how to handle user queries, it specifically includes an 'Auto-Clarity Exception' that prioritizes security warnings and clarity over the persona, reducing risk.
Audit Metadata