breeze
Warn
Audited by Snyk on Apr 22, 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.md "Running actions" and "Proxy requests" sections instruct the agent to use Membrane to run actions like list-cards/get-card and to proxy arbitrary Breeze API endpoints, which fetch user-generated/open Breeze data the agent will read and that can influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata