groovehq
Warn
Audited by Snyk on Apr 24, 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.md shows the agent will fetch and read user-generated GrooveHQ data via Membrane actions and proxy requests (e.g., "list-messages", "get-message", "list-tickets" and the "membrane request" proxy) which are third-party customer/support messages and could contain instructions influencing agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata