literature-downloader

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 ingests external, untrusted web content (e.g., scripts/download_accessible_fulltexts.py calls urllib to retrieve arbitrary pdf/HTML/XML URLs including doi.org and publisher pages, and SKILL.md/litplan.py direct agents to Google Scholar, PubMed, Crossref, Unpaywall, publisher pages and other public sites), and that fetched content is parsed and used to decide download status and next actions—creating a clear path for indirect prompt injection.