feishu-cli-auth

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs the agent to receive, store, and pass opaque credential-like strings (device_code, app_secret, access_token, refresh_token) verbatim between commands (e.g., --device-code "O-NU..." and JSON outputs containing app_secret/access_token), which forces the LLM to handle and potentially emit secrets directly.