pubmed
Warn
Audited by Snyk on Mar 13, 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 plainly fetches and ingests content from the public PubMed/PubMed Central service (via https://pubmed.mcp.claude.com/mcp) — e.g., search_articles, get_article_metadata, and get_full_text_article — and the agent is expected to read and act on those article/full-text results as part of its workflow, so external third-party content could materially influence decisions or tool use.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata