caveman
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a restricted communication style ('caveman mode') focused on token efficiency. It does not perform any file system access, network operations, or credential handling.
- [SAFE]: No obfuscation, prompt injection, or remote code execution patterns were detected.
- [SAFE]: The skill includes an 'Auto-Clarity Exception' that prioritizes security and safety by temporarily disabling the terse persona when presenting security warnings or confirming irreversible actions, which follows security best practices for AI agent communication.
Audit Metadata