tooluniverse-literature-deep-research

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 2 "Literature Search" and "Full-Text Verification Strategy" explicitly instruct the agent to fetch and extract snippets from open/public third-party sources (Europe PMC, PubMed/PMC, Semantic Scholar, ArXiv, bioRxiv/medRxiv, OpenAlex, Crossref, etc.) and to read/interpret those full-text snippets to grade evidence and drive synthesis/next actions, so untrusted external content can materially influence tool use and decisions.