WelsonJS LLM calls made through lib/language-inference-engine.js, and MCP tool results returned by mcploader.js, are gated by the LLM guard built into WelsonJS.Launcher (POST /llm-guard/inspect, called through lib/llm-guard.js).
Safe content may be sent to the selected remote provider or returned to the MCP client.Controversial content must pass a user-supplied anonymizer. Until one is registered with llm-guard.setAnonymizer, it is blocked.Unsafe content is never sent remotely: LLM requests are routed only to the local llamacpp provider, and MCP tool results are replaced by an error.Jailbreak category is blocked under any label, including Controversial: an anonymizer has nothing to mask in a prompt injection, so it cannot make it safe. LLM requests stop (they are not routed to the local model either), and MCP tool results are replaced by an error.The guard is on by default. It is switched off on the JavaScript side with ALLOW_UNSAFE_OUTBOUND = true in app.js or require("lib/llm-guard").setEnabled(false) at runtime; data then leaves unchecked, and inspect() reports "unchecked" instead of a verdict. Despite the general name, the switch only affects the two paths above; other outbound requests are not checked either way.
The model can be installed with the post-install component qwen3guard_06b together with llamacpp. The launcher selects the model by the LlmGuardModel setting (app.config, falling back to the built-in resource default qwen3guard_06b), the router model name; the router uses the .gguf file in:
%APPDATA%\WelsonJS\qwen3guard_06b\
The anonymizer is deliberately an injection point rather than a regex implementation. It must be implemented and reviewed for the application’s data types before enabling Controversial traffic.
See llm-guard-flow.en.md for the full flow.