feishu-doc-to-dev-spec

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses user-provided Feishu document URLs (see SKILL.md step "读取文档内容" and scripts/fetch_feishu_doc.py), so the agent ingests arbitrary user-generated Feishu cloud documents which are then analyzed and used to drive generation/decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). This skill reads user-supplied Feishu documents at runtime (e.g., https://xxx.feishu.cn/docx/xxxxx) via the Feishu API (https://open.feishu.cn/open-apis) and injects that fetched document content into the agent flow to drive prompts/results, so the external URLs are required and directly control the agent's instructions.