defuddle — 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

  warn

  The skill installs a third-party Node.js package and executes shell commands using user-provided URLs, which could lead to command injection if inputs are not properly sanitized. It also processes external web content, creating a surface for indirect prompt injection.

  Risk: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTIONMar 4, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · No issues

  Risk: MEDIUMMar 4, 2026Full report

• Runlayer

  pass

  1/1 file flagged

  Risk: LOWMar 4, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report