skills/polya20/grill-me/caveman/Gen Agent Trust Hub

caveman

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious behavior detected. The skill focuses solely on modifying the AI's linguistic style to optimize token usage.
  • [SAFE]: The skill includes safety-focused exceptions, specifically instructing the agent to suspend the 'caveman' style when providing security warnings or confirming irreversible actions, which demonstrates security best practices in prompt design.
  • [SAFE]: There are no external dependencies, network operations, or file system interactions associated with this skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 03:36 AM
Security Audit — agent-trust-hub — caveman