project-health — security audits

Review recommended

Independent security partners scan this skill's files for malicious content, prompt injection and risky patterns. Verdicts below come from the skills.sh audit program; each partner links to its full report.

• Gen Agent Trust Hub

  warn

  This skill manages project configuration by providing extensive permission presets and using sub-agents for repository analysis. It includes high-risk command patterns (sudo, curl, rsync) in its recommended configurations and employs dynamic script generation and execution for its health audits, which increases the potential attack surface.

  Risk: MEDIUMCOMMAND_EXECUTIONDATA_EXFILTRATIONREMOTE_CODE_EXECUTIONPROMPT_INJECTIONMar 14, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWMar 14, 2026Full report

• Runlayer

  warn

  3/6 files flagged

  Risk: MEDIUMMar 14, 2026Full report

• ZeroLeaks

  pass

  2 findings · Score: 80/100

  Risk: LOWApr 16, 2026Full report