literature-review

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly instructs the agent to fetch and read papers from public third‑party sources (e.g., "paper-search semanticscholar ..." and "paper skim <arxiv_id>" / Google Scholar / arXiv), meaning it ingests untrusted external content that can influence follow-up searches and analysis.