We (Cloudflare OS) run an app's client-side code in a null-origin iframe sandbox that is denied access to everything that we can possibly deny access to. Its only communication line to the outside world is via a Cap'n Web RPC session over postMessage() to the parent frame, which in turn forwards the session on to the app's own server, which runs in a Dynamic Worker sandbox on its end. So the app client can only talk to the app server and nothing else.

Or at least, ideally. Unfortunately, content-security-policy today has a few exotic holes. WebRTC, for instance, cannot be blocked; the standard simply doesn't cover it.

So it's not suitable as a sandbox against malicious code trying to leak data by any means possible. Instead it's protection against the AI doing something stupid, perhaps prompted by a user who doesn't know better.

(We would love to get those CSP holes plugged, though...)