feishu-update-doc

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly instructs using the whiteboard tag from a warning (e.g., <whiteboard token="xxx"/>) as the selection_with_ellipsis when submitting a replace_range, which requires the model to copy that token value verbatim into requests/outputs and thus risks exfiltrating a secret-like token.