surprise-me — 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 creates a significant security risk by dynamically discovering and executing instructions from other skills without user oversight. Its 'surprise' design explicitly discourages transparency, making it an ideal vector for indirect prompt injection or 'confused deputy' attacks where a malicious skill could be triggered and executed silently.

  Risk: HIGHPROMPT_INJECTIONFeb 17, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · No issues

  Risk: MEDIUMFeb 17, 2026Full report

• Runlayer

  warn

  1/1 file flagged

  Risk: MEDIUMFeb 21, 2026Full report