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 citation-workflow.md explicitly require searching and fetching papers from public third-party sources (e.g., Exa MCP, Semantic Scholar, CrossRef, arXiv) and the included Python CitationManager code performs runtime HTTP requests and reads abstracts/BibTeX to verify citations, so untrusted public content is ingested and can directly affect citation verification and drafting decisions.