latex-paper-en

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

• Third-party content exposure detected (high risk: 0.80). The skill's bibliography/citation workflow and CITATION_VERIFICATION.md explicitly instruct programmatic searches and retrievals from public APIs and sites (e.g., Semantic Scholar, arXiv, CrossRef/doi.org and Exa MCP) and the bibliography module references this verification flow, which means the agent will fetch and interpret open third‑party content as part of its required workflow.