academic-writer

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md "Writing Workflow" step 2 and the "Literature Search" / "Practical Commands" sections) explicitly instructs the agent to fetch and ingest papers from open/public third‑party sources (Google Scholar via webfetch, arXiv API, Semantic Scholar, DBLP), and those results are used to build literature matrices and drive citation/structure decisions, so untrusted external content can directly influence agent actions.