chat-sdk

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

• Third-party content exposure detected (high risk: 0.90). The SDK clearly ingests untrusted user-generated chat content (e.g., message.text from bot.onNewMention and bot.onSubscribedMessage) and explicitly shows using that content as prompts for an agent (see the ToolLoopAgent example where agent.stream({ prompt: message.text })), so third‑party messages can influence tool use and actions.