fountain
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.md explicitly instructs using Membrane to proxy requests to the Fountain API (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and "membrane action run"), which fetches user-generated/third-party Fountain content that the agent would read and act on.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata