feishu-doc-optimizer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs using a document token as a direct command-line argument (e.g., python3 ... <doc_token>) and to extract the token from the URL, which requires embedding secret-like tokens verbatim in commands/outputs and therefore risks exfiltration.

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly reads arbitrary Feishu document content via the Feishu API (SKILL.md "读取文档内容" and scripts/feishu_doc_reader.py) and then analyzes and uses that user-generated document content to drive edits through scripts/feishu_doc_editor.py, so untrusted third‑party content can materially influence the agent's actions.