smooch
Warn
Audited by Snyk on May 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). This skill explicitly instructs the agent to use the Membrane CLI to interact with Smooch data (see "This skill uses the Membrane CLI to interact with Smooch" and the "Conversation
- Message
- User" sections and the membrane action run examples), which means the agent will fetch and read user-generated messages from third-party customers that could contain untrusted instructions influencing subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata