gorgias
Warn
Audited by Snyk on Apr 21, 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 connects to Gorgias via Membrane (e.g., using "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") and works with Ticket/Message objects, meaning the agent will fetch and read user-generated third-party ticket/message content from an external system that could contain injected instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata