feishu-chat-monitor

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

• Third-party content exposure detected (high risk: 0.70). The skill's runtime script (scripts/check_missed_mentions.py) explicitly fetches user-generated messages from Feishu via GET https://open.feishu.cn/open-apis/im/v1/messages for the configured MONITORED_CHATS and reads message bodies/mentions to decide whether to send automated catch-up replies, so untrusted third-party chat content is ingested and directly influences actions.