agent-channelbot

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and interprets user-generated messages from Channel Talk workspaces via the agent-channelbot API (see SKILL.md and references/common-patterns.md: "snapshot", "message list", "message grep", and the templates that auto-respond/close chats), so untrusted third-party chat content can directly influence agent actions.