landbot
Warn
Audited by Snyk on Apr 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: 0.70). This skill reads user-generated customer data and messages from Landbot via Membrane actions (e.g., list-customers, get-customer) and the Membrane proxy request to the Landbot API, and those retrieved messages can be interpreted by the agent and used to drive follow-up actions like assign/block/delete, allowing indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata