caveman
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and modifies the linguistic style of the agent's output without introducing any security vulnerabilities or dangerous capabilities.
- [SAFE]: No evidence of data exfiltration, credential access, or privilege escalation was found. The skill operates entirely within the conversational context.
- [SAFE]: The 'Auto-Clarity Exception' section demonstrates a security-conscious design by ensuring that security warnings and destructive action confirmations are delivered in clear, unambiguous language rather than the 'caveman' persona.
- [NO_CODE]: There are no scripts, dependencies, or command executions included in the skill.
Audit Metadata