tooluniverse-literature-deep-research

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

• Third-party content exposure detected (high risk: 1.00). The skill's required Phase 2 "Literature Search" workflow explicitly calls public literature tools (e.g., EuropePMC_search_articles, PubMed_search_articles, SemanticScholar_search_papers, ArXiv/BioRxiv PDF snippet extraction) to fetch and ingest open/public third‑party articles and snippets, which the agent is expected to read and interpret to grade evidence and drive decisions in the report.