literature-review

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and ingest open/public third‑party content (e.g., PubMed, bioRxiv/medRxiv, arXiv, Semantic Scholar, Google Scholar and arbitrary scraped/full‑text URLs via gget, direct APIs, and search_databases.py) — content that is untrusted/user‑generated and that the agent is expected to read and interpret as part of its workflow, enabling indirect prompt injection.