caveman
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for modifying the agent's communication style. It does not contain any executable code, shell commands, or network operations.
- [SAFE]: Includes explicit safety boundaries (Auto-Clarity) that instruct the agent to drop the 'caveman' style when presenting security warnings, irreversible actions, or technically ambiguous instructions.
- [SAFE]: The persistence mentioned in the skill refers to maintaining the conversational persona across dialogue turns, which is intended behavior and not a system-level persistence attack.
- [SAFE]: Frontmatter configuration includes 'disable-model-invocation: true', which is a restrictive measure that limits the skill's execution environment.
Audit Metadata