systematic-review
Warn
Audited by Snyk on Apr 6, 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). The skill explicitly performs multi-database searches against public sources (PubMed/MEDLINE, arXiv, Semantic Scholar, CrossRef) and uses ScienceClaw to ingest and extract content from PDF full texts, so it clearly consumes untrusted, third-party web content that the agent must read and that can materially influence screening, extraction, and analysis decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata