whatsapp-cloud-api

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime LLM context is fed by webhook POST payloads (Meta WhatsApp events) that include outsider-authored free text such as message.text.body and interactive.*.response_json, which are then used as userMessage/flow response in the agent’s conversation/AI handling path.