Claude Code Templates: Unauthenticated OS command injection (RCE) in Claude Code Studio server (--studio)

Summary

npx claude-code-templates --studio launches "Claude Code Studio", an Express HTTP server (cli-tool/src/sandbox-server.js, default port 3444) that binds to all interfaces (0.0.0.0), sets Access-Control-Allow-Origin: *, and requires no authentication. Two POST endpoints pass attacker-controlled request-body fields into child_process.spawn(..., { shell: true }). Because shell: true makes Node join the argv array into a single sh -c string, the fields are parsed by the shell and metacharacters execute. Any unauthenticated attacker who can reach the port — a malicious web page the developer visits, or anyone on the same LAN — can execute arbitrary OS commands on the developer's machine.

Details

In cli-tool/src/sandbox-server.js:

• app.listen(PORT, ...) is called with no host argument, so the server listens on 0.0.0.0 / :: (reachable from the LAN, not just localhost).
• The CORS middleware sends Access-Control-Allow-Origin: * and answers the preflight OPTIONS for any origin, so a browser will deliver cross-origin POSTs to it.
• There is no authentication on any endpoint.

The vulnerable sinks:

1. POST /api/execute — the prompt body field flows into executeLocalTask():

   const child = spawn('claude', [finalPrompt], { /* ... */ shell: true });
   The only validation on prompt is a length check (>= 10 chars). With shell: true, finalPrompt is interpreted by the shell.
   
   

2. POST /api/install-agent — the agentName body f…