discord

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill uses the Membrane CLI to connect to Discord and run actions that retrieve Discord channel messages and user data (user-generated, public third‑party content) as part of its core workflow (see "Connecting to Discord" and "Running actions" where action run returns output), so untrusted content could influence agent behavior.