biorxiv-database
Warn
Audited by Snyk on Feb 16, 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). The skill directly fetches and ingests public, user-generated preprint content from bioRxiv (e.g., via BASE_URL "https://api.biorxiv.org" in scripts/biorxiv_search.py and by downloading PDFs from "https://www.biorxiv.org/content/...v{version}.full.pdf"), including abstracts, JATS XML and full-text PDFs which the agent reads and formats, so it clearly consumes untrusted third‑party content that could carry embedded instructions.
Audit Metadata