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 broad searches of the local filesystem and ingests data from external websites, creating potential for sensitive data exposure and indirect prompt injection.

  Risk: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTIONMay 15, 2026Full report

• Socket

  pass

  No alerts

  May 15, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMMay 15, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 15, 2026Full report