agents-router
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). The skill can spawn a "researcher" agent for "Web research" (see Decision Tree / Agent Selection Matrix) which explicitly implies fetching and ingesting public web content, exposing the agent to untrusted third-party sources that could carry indirect prompt injection.
Audit Metadata