biorxiv-search

Warn

Audited by Snyk on Apr 12, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests public, user-generated preprint metadata and text from the official bioRxiv API (see SKILL.md "Base API: https://api.biorxiv.org/details/biorxiv" and scripts/search.py's fetch_json/build_url logic), and the agent directly reads and uses titles/abstracts/authors to drive matching and subsequent results, so untrusted third-party content can influence its behavior.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 12, 2026, 02:58 AM
Issues
1