web-scraping — 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

  fail

  The skill provides comprehensive patterns for web scraping using standard Python libraries. A homoglyph was detected in a class name, which is a technique often used to evade security scanners or signature detection. Additionally, because the skill is designed to extract content from external websites and feed it into the agent context, it presents an inherent surface for indirect prompt injection attacks.

  Risk: HIGHPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONMay 9, 2026Full report

• Socket

  warn

  1 alert: gptAnomaly

  May 9, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 1 issue

  Risk: MEDIUMMay 9, 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