feishu-message-recall

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

• Third-party content exposure detected (high risk: 0.90). The skill's scripts/recall.py explicitly calls Feishu's open API (get_thread_messages() → https://open.feishu.cn/open-apis/im/v1/messages) to fetch user-generated thread messages and then reads/filters those messages to decide and perform deletions, so untrusted third-party content can directly influence tool actions.