twitch-ai-chatbot

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text from Twitch chat messages (authored by viewers) is read over the runtime WebSocket IRC connection and then ingested into the LLM prompt via handle_raw() → self.chat_history → trigger_handler() building chat_context and prompt for _call_anthropic().