bot-channel-task

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

• Third-party content exposure detected (high risk: 1.00). The skill directly ingests channel messages from third-party sources (e.g., plugin:telegram channel messages) and uses that user-generated content to classify tasks, launch background agents, and invoke tools (e.g., /bot-jobs), so untrusted content can materially influence agent actions.