citation-management

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and scrapes public third‑party sites (e.g., search_google_scholar.py, search_pubmed.py and extract_metadata.py in SKILL.md) — including Google Scholar, publisher URLs/arbitrary URLs, CrossRef, PubMed and arXiv — and ingests that untrusted web content into automated metadata extraction, validation and auto‑fix workflows that can materially influence tool actions and next steps.