validation-sprint
Warn
Audited by Snyk on Mar 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The Phase 2 teammate prompts explicitly instruct agents to "Search for evidence in forums, review sites, and community discussions" and to "Use WebSearch" (public, user-generated sources) and those findings are required inputs for the synthesis/verdict, so untrusted third-party content can directly influence tool use and decisions.
Audit Metadata