humanize — 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 acts as a wrapper for an external text humanization service. It transmits user-provided content to a non-whitelisted third-party domain (humanizerai.com) and lacks sanitization or boundary markers for the ingested text, creating a surface for potential indirect prompt injection.

  Risk: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONFeb 17, 2026Full report

• Socket

  warn

  1 alert: gptSecurity

  Mar 18, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · No issues

  Risk: MEDIUMFeb 15, 2026Full report

• Runlayer

  warn

  1/1 file flagged

  Risk: MEDIUMFeb 22, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report