create-boss

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

• Third-party content exposure detected (high risk: 0.90). The skill includes required workflows and tools that fetch and ingest untrusted, user-generated content (e.g., feishu_auto_collector.py, dingtalk_auto_collector.py, slack_auto_collector.py, feishu_browser.py, social_parser.py, wechat_parser.py and the Step 2 "素材导入" / SKILL.md analysis steps), and the agent is expected to read/interpret those external chats/docs to build the boss persona and drive downstream actions, so third‑party content can materially influence tool behavior.