wails

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The docs explicitly recommend embedding an MCP server (WAILS_MCP=1) that lets LLM agents remotely control the app (window control, DOM inspection, bound-method calls) and also document serving HTTP routes from services — both are deliberate remote-access patterns that can be abused as backdoors or for data exfiltration.