literature-review
Warn
Audited by Snyk on Mar 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to search and ingest content from open public sources (e.g., "gget search pubmed", bioRxiv, arXiv, Semantic Scholar, Google Scholar scraping) and to obtain and read full texts and aggregated JSON results as part of the mandatory literature-search and screening workflow, so third‑party content can directly influence screening, extraction, and downstream decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata