feishu-doc

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

• Third-party content exposure detected (high risk: 0.80). The skill directly fetches and ingests user-generated Feishu (Lark) Wiki/Docs/Sheets/Bitable content from the open.feishu.cn APIs (see SKILL.md and the fetch calls in index.js and lib/docx.js, lib/bitable.js, lib/sheet.js, lib/wiki.js), so untrusted third‑party content is read and converted into Markdown and can influence subsequent agent behavior.