biorxiv-database

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

• Third-party content exposure detected (high risk: 0.90). This skill programmatically fetches metadata, abstracts, and PDFs from the public bioRxiv API and web pages (e.g., https://api.biorxiv.org and https://www.biorxiv.org) as shown in scripts/biorxiv_client.py and SKILL.md, ingesting untrusted third-party content that is parsed and used to drive search results and downstream actions.