deep-research — 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 deep-research skill automates structured academic literature reviews by searching and processing research papers. It contains a high-severity security finding due to instructions directing the agent to read credentials from a sensitive local file. Additionally, the ingestion of external PDF content creates a surface for indirect prompt injection attacks.

  Risk: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADSFeb 27, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  warn

  Risk: MEDIUM · No issues

  Risk: MEDIUMFeb 27, 2026Full report

• Runlayer

  warn

  4/11 files flagged

  Risk: MEDIUMFeb 27, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report