skills/mattpocock/skills/caveman/Gen Agent Trust Hub

caveman

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill exclusively defines a communication style to minimize token consumption by removing filler words and articles while maintaining technical accuracy.
  • [SAFE]: No external dependencies, package installations, or remote code execution patterns were detected.
  • [SAFE]: No network operations, sensitive file access, or data exfiltration risks are present.
  • [SAFE]: The 'Persistence' section describes maintaining a conversational persona across turns rather than any malicious system-level persistence.
  • [SAFE]: Includes a safety-first 'Auto-Clarity Exception' that instructs the agent to revert to normal speech for security warnings and irreversible action confirmations to prevent user misunderstanding.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 06:26 PM
Security Audit — agent-trust-hub — caveman