dingtalk-teambition

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

• Third-party content exposure detected (high risk: 0.70). The skill fetches and parses user-generated Teambition content (comments, task notes, rich-text HTML and attachments) from the Teambition API (e.g., scripts/query_task_activity.py calling v3/task/{taskId}/activity/list, scripts/render_rtf.py calling v3/task/rtf/render, and scripts/query_task_detail.py calling v3/task/query), so the agent ingests untrusted third-party user content that it will read/interpret as part of its workflow and which could influence subsequent actions.