discord

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

• Third-party content exposure detected (high risk: 0.90). This skill's SKILL.md instructs the agent to connect via the Membrane CLI to Discord and to proxy requests to the Discord API (e.g., "membrane request CONNECTION_ID /path/to/endpoint" and action list/run workflows), which will fetch untrusted, user-generated content (Discord messages/posts) that the agent is expected to read and that could influence subsequent actions.