literature-review
Warn
Audited by Snyk on Jun 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can ingest outsider-authored free text from public literature sources (e.g., PubMed/bioRxiv/arXiv/Semantic Scholar results and abstracts, and potentially full-text) into the agent’s context via the “Abstract/full-text screening” and “write thematic synthesis” phases, where retrieved titles/abstracts are used to generate the review.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata