whatsapp-cloud-api-agent

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly receives and parses untrusted, user-generated WhatsApp messages from Meta webhooks (see POST /webhook handling of value.messages in SKILL.md and scripts/webhook_handler.py) and uses their text to classify, route, and dispatch actions to agents, so third-party content can influence tool use and next steps.