deep-research — 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

  pass

  The skill performs deep research by retrieving and processing external web content. It contains a surface for indirect prompt injection as it lacks specific sanitization or boundary markers for untrusted data fetched from the web.

  Risk: SAFEPROMPT_INJECTIONMay 13, 2026Full report

• Socket

  pass

  No alerts

  May 13, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 2 issues

  Risk: MEDIUMMay 13, 2026Full report

• Runlayer

  pass

  1 file scanned · No issues

  Risk: NONEMar 13, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report