medical-imaging-review
Warn
Audited by Snyk on Mar 31, 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's required workflow (references/WORKFLOW.md and references/MCP_SETUP.md) explicitly instructs the agent to use ArXiv MCP (search_papers, download_paper, read_paper), PubMed MCP, Zotero, and web searches (IEEE/Springer/Google Scholar), which fetch and ingest open/public third-party papers and web content that the agent is expected to read and act on when composing the review, exposing it to untrusted user-generated/preprint content that could carry indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata