harness-similarity

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected in the skill instructions.\n- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute npx ruflo metaharness similarity. This is the intended functionality for calculating similarity scores from JSON files using the vendor's CLI tool.\n- [EXTERNAL_DOWNLOADS]: The skill references internal project scripts (e.g., ../../scripts/_similarity.mjs) to provide core logic, which is consistent with its role as a repository-integrated tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:09 PM
Security Audit — agent-trust-hub — harness-similarity