caveman

Pass

Audited by Gen Agent Trust Hub on Apr 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary purpose is to modify the agent's communication style for token efficiency. It does not request any tool access, perform network operations, or access the file system.
  • [SAFE]: No prompt injection patterns were found. The instructions focus on linguistic compression (dropping articles and filler words) while explicitly mandating that technical substance and code blocks remain unchanged.
  • [SAFE]: The skill includes safety-conscious rules under 'Auto-Clarity', instructing the agent to drop the caveman persona for security warnings and destructive action confirmations to ensure user clarity during critical operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 12, 2026, 09:26 AM
Security Audit — agent-trust-hub — caveman