WorldThreatModelHarness
Warn
Audited by Snyk on Mar 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly invokes Research/WebSearch to fetch public web content (see Workflows/UpdateModels.md "RESEARCH: Use WebSearch..." agent prompt and Workflows/TestIdea.md "Research update check") and ingests those findings into world models and analyses that directly drive recommendations, so untrusted third-party content can materially influence behavior.
Audit Metadata