pua-ja — 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

  pass

  This skill uses high-pressure corporate personas and aggressive instructions to force the AI to be more proactive and thorough. It mandates the use of command execution and network tools while discouraging the AI from refusing tasks or asking for user input.

  Risk: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONMar 23, 2026Full report

• Socket

  warn

  1 alert: gptAnomaly

  Mar 23, 2026Full report

• Snyk

  fail

  Risk: HIGH · 3 issues

  Risk: HIGHMar 23, 2026Full report

• Runlayer

  warn

  1/1 file flagged

  Risk: MEDIUMMar 15, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report