ai-gateway-management

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly shows passing API keys/tokens verbatim in CLI commands and Authorization headers (e.g., --token "sk-xxx" and curl -H "Authorization: Bearer "), which requires the LLM to emit secret values directly into generated commands/outputs.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.80). The skill instructs creating services/routes, modifying gateway and OpenClaw configuration files (including /root/manager-workspace/openclaw.json) and starting servers under /opt, which change system state and likely require elevated privileges and could compromise the host if misused.