Hacker News new | past | comments | ask | show | jobs | submit
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.
loading story #50420105
I configured remote VPS and cloudflare sandboxes to run my agents.
Who says that such options necessarily need to exist?
loading story #50419331