Hacker News new | ask | show | jobs
by Nition 149 days ago
I'm currently stuck on Windows, but I thought sandboxing was built in to Claude Code as a feature on Linux with the /sandbox command?
3 comments

For Windows a quick win is to install VMware Workstation Pro (which is free) and install Ubuntu 24.04 LTS as a VM.

Broadcom bought VMware then released Workstation Pro for free and I don't think they kept the download link but you can get from TechPowerUp:

https://www.techpowerup.com/download/vmware-workstation-pro/

You can then let LLMs on YOLO mode inside it.

What is the advantage of using VMware Workstation Pro for this as opposed to using WSL2?
I think it has default access to your c drive via a mount, for one. You could add layers/sandboxes, but it’s not isolated.
Funny, but I wrote some environment initialization and setup scripts that you just unzip to a new dev desktop, and run the first powershell script, and it will work through (have to reboot after a couple installs), but it goes through, then once WSL is up, it'll rely on the /mnt/c/ paths to run bash scripts to initialize the wsl environment too... was pretty handy.
Yeah, I do most Linux stuff on Windows in containers using podman leveraging WSL2, but that's a good point.
I wouldn't put it past Opus 4.5 in yolo mode to vm escape if it felt like it haha
Stronger isolation and choice of OS
Windows has the WSL for native Linux vms, these days (and also the past ~decade)
I can rm -rf Windows files from WSL2. And so can LLMs.

Meanwhile a VM isolates by default.

You can turn all the interop and mounting of the windows FS with ease. I run claude in yolo mode using this exact setup. Just role out a new WSL env for each claude I want yoloing and away it goes. I suppose we could try to theorize how this is still dangerous buts its getting into extremely silly territory.
That's great to know! And important to clarify because by default WSL has access to all disks.
/sandbox AFAIK uses https://github.com/anthropic-experimental/sandbox-runtime under the hood.

It's still experimental and if you dive into the issues I would call its protection light. Many users experiences erratic issues with perms not being enforced, etc.

For me the largest limitation was that it's read-mode is deny-only, meaning that with an empty deny-list it can read all files on your laptop.

Restricting to specific domains have worked fine for me, but it can't block on specific ports, so you can't say for instance you may access these dev-server ports, but not dev-server ports belonging to another sandbox.

It feels as though the primary usecase is running inside an already network and filesystem sandboxed container.

It’s pretty weak sandboxing. It still grants full read only access to the file system so any secrets in your home directory can still be exfiltrated. I’m pretty sure it could also be deceptive and use a script to write where it shouldn’t be able to as well. That’s not really sandboxing in my opinion. It should be something like unveil, the process gets a working space at startup, and it cannot ever do anything outside of that directory.