biorxiv-database
Warn
Audited by Snyk on Jun 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill fetches bioRxiv preprint metadata (including free-text
titleandabstract) from the public bioRxiv API at runtime (requests.gettohttps://api.biorxiv.org/details/biorxiv/.../.../details/biorxiv/{start}/{end}/{category}), and those fields are then formatted into JSON and can be passed into the agent’s LLM context as readable text—an outsider-authored source (preprint authors) via public web content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata