← Back to context

Comment by TheDong

24 days ago

It depends on what you're trying to prevent.

If your fear is exfiltration of your browser sessions and your computer joining a botnet, or accidental deletion of your data, then a sandbox helps.

If your fear is the llm exfiltrating code you gave it access to then a sandbox is not enough.

I'm personally more worried about the former.

5 comments

TheDong

Reply
jdkoeck  24 days ago

Code is not the only thing the agent could exfiltrate, what about API keys for instance? I agree sandboxing for security in depth is good, but it’s not sufficient and can lull you into a false sense of security.

  • twodave  24 days ago

    This is what emulators and separate accounts are for. Ideally you can use an emulator and never let the container know about an API key. At worst you can use a dedicated account/key for dev that is isolated from your prod account.

    • gessha  24 days ago

      VM + dedicated key with quotas should get you 95% there if you want to experiment around. Waiting is also an option, so much of the workflow changes with months passing so you’re not missing much.

      1 reply →