caveman
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: Stylistic instruction skill. The skill defines a persona for brief, technical communication to save tokens and improve skimming efficiency. No executable code or dangerous instructions are present.
- [SAFE]: Security best practices. The skill includes an 'Auto-Clarity Exception' that instructs the agent to drop the terse style for security warnings and irreversible action confirmations, ensuring that safety-critical information is always delivered clearly.
- [EXTERNAL_DOWNLOADS]: Metadata reference. The YAML frontmatter contains a 'derived-from' URL pointing to a public GitHub repository. This is a documentation reference and does not involve dynamic downloads or execution of code.
Audit Metadata