What are the sandboxing / isolation options that would protect against attacks like this?
Running Claude code in an isolated, temporary VM, with no access to memory is a good start. You give it your repo, prompt and you get back PRs. Claude code on web is a convenient way to do that.
I configured remote VPS and cloudflare sandboxes to run my agents.
Who says that such options necessarily need to exist?
Running Claude code in an isolated, temporary VM, with no access to memory is a good start. You give it your repo, prompt and you get back PRs. Claude code on web is a convenient way to do that.