deep-research — 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 'deep-research' skill is a sophisticated and highly disciplined 13-agent pipeline designed for rigorous academic research. It incorporates exceptional security and integrity controls, such as three-index API triangulation (Semantic Scholar, Crossref, OpenAlex) to detect hallucinated citations, temporal integrity logic to verify event timelines, and 'pattern protection' rules to prevent model drift. The skill uses standard utilities and well-known academic APIs for legitimate verification purposes, demonstrating a high degree of defensive design against common AI agent failure modes.

  Risk: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONMay 29, 2026Full report

• Socket

  pass

  No alerts

  May 29, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · 2 issues

  Risk: MEDIUMMay 29, 2026Full report

• Runlayer

  pass

  7/41 files flagged

  Risk: LOWMar 12, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report