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 explicitly instructs the agent to search and ingest public web content—e.g., "Recommended: Install Exa MCP" (https://mcp.exa.ai/mcp) in SKILL.md and the citation workflow in references/citation-workflow.md that calls Semantic Scholar, CrossRef, and arXiv APIs—to verify and fetch BibTeX, so the agent will read and act on untrusted third-party content as part of its workflow.