ensemble-team
Warn
Audited by Snyk on Mar 25, 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 requires using "WebSearch" to research and verify external experts (Phase 2: "Research each expert — ... Use WebSearch..." and references/role-catalog.md "Search for candidates: Use WebSearch to find"), meaning the agent will fetch and interpret open/public web content about third-party people which can materially influence expert selection, generated profiles, and subsequent team actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata