ultraqa — 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 establishes an autonomous cycle to run QA tools, diagnose failures, and automatically apply code fixes via subagents. This workflow is susceptible to indirect prompt injection if test outputs or build logs contain malicious instructions that could manipulate the diagnostic or executor agents into making unsafe code changes.

  Risk: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONMay 29, 2026Full report

• Socket

  warn

  1 alert: gptAnomaly

  May 29, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWMay 29, 2026Full report

• Runlayer

  warn

  1/1 file flagged

  Risk: MEDIUMFeb 21, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report