feishu-chat-extractor

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches and ingests user-generated Feishu/Lark group chat messages via the Feishu API (see scripts/extract_chat.py and monitor_external_aj.py / monitor_with_intimacy.py) and then analyzes that content to update group memory, intimacy scores and generate reports, so arbitrary third‑party messages can materially influence agent behavior.