using-superpowers — 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

  This skill establishes a meta-workflow that forces the agent to prioritize loading and following external instruction files (skills) before performing any task. It uses aggressive language to override standard agent reasoning and significantly expands the attack surface for indirect prompt injection by lowering the threshold for external tool invocation.

  Risk: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONDATA_EXFILTRATIONREMOTE_CODE_EXECUTIONMay 6, 2026Full report

• Socket

  warn

  1 alert: gptAnomaly

  May 6, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWMay 6, 2026Full report

• Runlayer

  pass

  2 files scanned · No issues

  Risk: NONEMar 11, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report