feishu-lark-agent

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires supplying app tokens/credentials as command-line arguments (e.g., --app APP_TOKEN and "App token in URL"), so an LLM assisting with concrete commands may be forced to emit secret values verbatim, creating an exfiltration risk.