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 SKILL.md and references/citation-workflow.md explicitly require searching and programmatically fetching content from open third‑party sources (e.g., Exa MCP, Semantic Scholar, CrossRef, arXiv) and instruct the agent to read and verify those papers/BibTeX entries as part of the citation workflow and drafting decisions, exposing the agent to untrusted external content that can influence subsequent actions.