whatsapp-by-online-live-support

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md instructs the agent to connect to WhatsApp via Membrane and to run actions or proxy requests (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") which will fetch and expose user-generated WhatsApp messages and content that the agent is expected to read and act on, creating a clear avenue for indirect prompt injection.