medical-imaging-review

Warn

Audited by Snyk on Feb 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: 1.00). This skill explicitly instructs the agent to search, download, and read papers from open public sources (e.g., ArXiv via the arxiv-mcp-server, PubMed via pubmedmcp, and web searches/IEEE/Google Scholar) using tools like search_papers, download_paper, read_paper, and pubmed_search_articles, so it will ingest untrusted third-party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:53 PM