smartengage
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: 0.70). The SKILL.md shows the agent listing and running SmartEngage actions and using Membrane's "request" proxy to fetch arbitrary SmartEngage API endpoints (e.g., "membrane action list/run" and "membrane request"), which pulls third‑party/user-generated content from the SmartEngage service that the agent is expected to read and could materially affect subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata