product-showcase — 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

  The skill generates marketing websites by browsing applications, taking screenshots, and creating assets. It uses local tools and a short Python script to process images. Security considerations include the use of command-line arguments for credentials and the potential for indirect prompt injection when visiting external URLs.

  Risk: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTIONMay 14, 2026Full report

• Socket

  warn

  1 alert: gptSecurity

  May 14, 2026Full report

• Snyk

  fail

  Risk: HIGH · 2 issues

  Risk: HIGHMay 14, 2026Full report

• Runlayer

  pass

  1 file scanned · No issues

  Risk: NONEMar 16, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report