keycloak
Warn
Audited by Snyk on Apr 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to connect to arbitrary external Keycloak endpoints via the Membrane CLI and proxy (e.g., membrane connection ensure and membrane request), and to read connection/clientAction fields such as clientAction.description and clientAction.agentInstructions returned by those external connections, meaning the agent ingests and can act on untrusted third-party content from external apps/APIs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata