sendbird

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md shows using Membrane to run actions and proxy requests to the Sendbird API (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which will fetch user-generated chat/channel messages from a third-party service that the agent is expected to read and act on, so untrusted external content could inject instructions.