identity-manager

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

• Third-party content exposure detected (high risk: 0.70). The skill fetches and ingests user-generated group and member data from third-party Feishu APIs (sync.js calling https://open.feishu.cn/open-apis/...) and via the group-intel fetch script invoked by auto_scan.js, so it clearly reads untrusted public/user-provided content as part of its workflow.