literature-review-writer

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

• Third-party content exposure detected (high risk: 0.80). Yes — the skill's required workflow (Step 2 "检索真实文献（WebSearch）" and the verification steps in references/verification-guide.md) explicitly instructs the agent to fetch and ingest content from public sites (e.g., scholar.google.com, journals.sagepub.com, sciencedirect.com and databases like Google Scholar/CNKI), so untrusted third‑party content is read and used to decide which literature to include.