groom
Warn
Audited by Snyk on Feb 23, 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 explicitly requires using "Gemini — Web-grounded research" (Phase 4: "Use Gemini for current best practices research"), which implies fetching and ingesting open/public web content that the agent will read and use to shape recommendations and issue-creation decisions.
Audit Metadata