There's no antivirus or firewall today that can protect your files from the ability this could have to wreck havoc on your network, let alone your computer.
This scene comes to mind: https://makeagif.com/i/BA7Yt3
We treat it as what it is - another user. Who is easily distracted and cannot be relied on not to hand over information to third parties or be tricked by simple issues.
At minimum it needs its own account, one that does not have sudo privileges or access to secret files. At best it needs its own VM.
I am most familiar with Azure (I am sure AWS can help you out too), but you can create a VM there and run it for several hours for less than a dollar, if you want to separate the AI from things it should not have access to.
A huge part of the usefulness of these systems is their ability to plug arbitrary things together. Which also means arbitrary holes. Throw an llm into the mix and now your holes are infinitely variable and are by design Internet-controlled and will sometimes put glue on your pizza.
A (production) system like this is already such a daemon. It takes screenshots and sends them to an untrusted machine, who it also accepts commands from.
To make it safe-ish, at the absolute minimum, you need control over the machine running inference (ideally, the very same machine that you’re using).