last30days — security audits

Flagged by auditors

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

  fail

  This skill performs high-risk credential harvesting by programmatically extracting and decrypting browser cookies (Chrome, Safari, Firefox) and retrieving secrets from the macOS Keychain. It also contains instructions designed to override the AI agent's standard operating protocols and tool requirements.

  Risk: HIGHCREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTIONMay 18, 2026Full report

• Socket

  warn

  1 alert: gptAnomaly

  May 18, 2026Full report

• Snyk

  fail

  Risk: HIGH · 2 issues

  Risk: HIGHMay 18, 2026Full report

• Runlayer

  fail

  304/604 files flagged

  Risk: HIGHMar 15, 2026Full report

• ZeroLeaks

  warn

  Scan incomplete

  Apr 16, 2026Full report