bioinformatics-scientist

Warn

Audited by Snyk on Mar 31, 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's system prompt and workflow explicitly require literature/database lookups (e.g., §1.3 "Literature support: PubMed search" and the References/§11 listing public resources like gnomAD, ClinVar, GATK/ACMG URLs) and the platform install notes (references/5-platform-support "Read [URL]") indicate the agent is expected to fetch and interpret open/public third‑party content that can materially influence analysis and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 31, 2026, 06:23 AM
Issues
1