citation-management

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and scripts (e.g., scripts/search_google_scholar.py, scripts/search_pubmed.py, and scripts/extract_metadata.py --url) explicitly fetch and ingest content from public third‑party sources (Google Scholar, PubMed, CrossRef, arXiv, doi.org and arbitrary URLs) and use that content to extract/validate metadata and drive actions (BibTeX generation, auto-fix, validation), so untrusted third‑party content can materially influence agent behavior.