compare-harnesses

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents a utility for performing a diff between two directory structures (harnesses). Analysis of the SKILL.md content shows no signs of prompt injection, data exfiltration, or unauthorized command execution. It correctly mentions a sanitization step for sensitive fields (secrets/tokens/keys) in its JSON output mode, which is a positive security practice. The skill uses local CLI commands for comparison tasks and does not reference untrusted external resources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 07:38 PM
Security Audit — agent-trust-hub — compare-harnesses