deep-literature-search
Warn
Audited by Snyk on Mar 31, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). Yes — the SKILL.md "Multi-Database Execution" and "Execution Checklist" sections explicitly require running searches and retrieving/exporting full texts and results from public academic databases (e.g., PubMed, Scopus, Web of Science, OpenAlex, arXiv, bioRxiv, SSRN, ProQuest), which means the agent would ingest and interpret third‑party web content that can materially influence screening and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata