scientific-computing

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: 0.70). The skill explicitly references BioPython capabilities that perform remote queries (e.g., "BLAST: Local and remote sequence alignment" and "NCBI Entrez: Database access") which fetch and parse public, user-contributed data from third‑party sources (NCBI), exposing the agent to untrusted external content it would read and interpret.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:26 PM