NYC

biomni

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: 0.80). Biomni automatically downloads and accesses ~11GB of public biomedical databases and literature (e.g., PubMed abstracts, Ensembl, UniProt, ClinVar) and can use MCP servers/web search, which the agent reads and interprets as part of its workflow, exposing it to untrusted third‑party content and potential indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 10:48 AM