chat-sdk

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and acts on user-generated messages from third-party chat platforms (e.g., Slack/Discord/Telegram) — see SKILL.md's event handlers and the streaming example where onNewMention uses message.text as the agent.prompt (agent.stream({ prompt: message.text })), so untrusted external content is read and can drive agent behavior.