skills/cryptognome/claude-kit/caveman/Gen Agent Trust Hub

caveman

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of natural language instructions and markdown formatting. It does not include any executable scripts, external dependencies, or system-level commands.
  • [SAFE]: The skill explicitly includes a "Safety override" protocol, instructing the agent to drop the compressed prose style and return to full clarity when handling security warnings, confirming destructive actions, or providing multi-step instructions that could be misread if fragmented.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 06:52 PM