biorxiv-database
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill directly searches and downloads content from the public bioRxiv preprint server (e.g., pdf_url/html_url entries like https://www.biorxiv.org/...), ingesting untrusted, user‑supplied abstracts and PDFs which the agent is expected to read and analyze, creating a clear avenue for indirect prompt injection.
Audit Metadata