feishu-cli-mail

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 reads user mailbox content (commands: mail message / messages / thread / triage and the "处理未读邮件" workflow which says "拿 message_id → 看内容 → 回复") and reply/reply-all will automatically include the original email body, so it ingests untrusted, user-generated email content that can influence sending/forwarding behavior.