hebrew-chatbot-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill's webhook and bot scaffolds explicitly ingest and process untrusted user-generated messages from public channels (see scripts/whatsapp-webhook-handler.py handling WhatsApp Cloud API webhook messages and scripts/telegram-bot-scaffold.py handling Telegram updates), and those messages are parsed to drive intents, state transitions, and actions—allowing third-party content to materially influence the agent's behavior.