caveman
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a formatting persona called 'caveman mode' to optimize token consumption. It does not perform any file system operations, network requests, or credential handling.
- [SAFE]: The 'Persistence' section describes maintaining a conversational state within the LLM's context, which is standard for persona-based skills and does not involve system-level persistence mechanisms like cron jobs or startup scripts.
- [SAFE]: The 'Auto-Clarity Exception' rule specifically mandates dropping the compressed style for security warnings and irreversible actions, demonstrating a security-conscious design.
- [SAFE]: No obfuscated content, remote code execution patterns, or prompt injection vulnerabilities were identified.
Audit Metadata