chunking-strategy — 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 provides a comprehensive framework and code examples for document chunking in RAG systems. It includes Python implementations that use the `pickle` library for caching, which is insecure when handling potentially untrusted data and can lead to arbitrary code execution. The skill also processes external documents and allows powerful system tools, creating a surface for indirect prompt injection.

  Risk: MEDIUMREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTIONMar 24, 2026Full report

• Socket

  pass

  No alerts

  Mar 24, 2026Full report

• Snyk

  pass

  Risk: LOW · No issues

  Risk: LOWMar 24, 2026Full report

• Runlayer

  warn

  9/9 files flagged

  Risk: MEDIUMFeb 25, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report