ml-paper-writing

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows (SKILL.md and references/citation-workflow.md) explicitly instruct programmatic searching and retrieval from public third-party sources—e.g., Semantic Scholar, CrossRef, arXiv (including arXiv search URLs), OpenAlex, and an external Exa MCP URL—and include code to fetch/verify BibTeX and paper content, so the agent will ingest untrusted public web content that can materially influence citation selection and drafting decisions.