literature-review

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests content from open/public third‑party sources (e.g., PubMed, bioRxiv/medRxiv, arXiv, Semantic Scholar and Google Scholar scraping as described in "Phase 2: Systematic Literature Search" and implemented via gget, API access, and scripts/search_databases.py and scripts/verify_citations.py), so the agent will read and interpret untrusted, user‑generated/public web content as part of its workflow.