feishu-doc-to-wechat-draft

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and ingests arbitrary Feishu/Lark documents via lark-cli (scripts/wechat_draft_publisher/lark_docs.py::fetch_lark_doc) and downloads remote images/URLs in pipeline.py, treating user-generated third‑party content as input that is parsed and used to drive rendering, uploads, and publish actions, so untrusted content can materially influence tool behavior.