openclaw-create-agent

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly collects and passes sensitive fields like app_secret as command-line arguments (e.g., --app-secret <app_secret>) and would instruct the agent to embed those secret values verbatim in generated commands/scripts, creating a high exfiltration risk.