Hacker News

points by kstenerud 4 hours ago | 0 comments

This is EXACTLY why I never use an agent outside of https://github.com/kstenerud/yoloai

I appreciate that you're trying to make Claude Code safer, but the agent really needs to be a lot more restricted in its reach rather than its actions.

The agent should NOT have ANY access to:

- Your ENV

- Your homedir

- The network at large

- ANY other directory on your system

- No, not even your workdir.

The only safe way to use an agent is COMPLETELY isolated by a container or VM, using git semantics to extract its output.

[–] post-it 3 hours ago

That's the only safe way to use any software that you haven't thoroughly reviewed. But that's not how I use any software.

[–] kstenerud 3 hours ago

You could in theory fully review Claude Code.

But even that wouldn't be enough because LLMs are nondeterministic, and these kinds of issues are the inevitable results.

Only a mechanical, deterministic failsafe can protect you from it.

[–] what 2 hours ago

> You could in theory fully review Claude Code.

Can you point me to the CC source code?

[–] kstenerud 2 hours ago

The CC source code leak was contained many months ago. But Claude is perfectly happy to decompile its own code if you ask the right way. It'll even patch the binary for you.

Regardless, It's kinda silly to keep the harness code hidden. There aren't any valuable secrets in there.

But there are rules & procedures to follow, so...

[–] what 1 hour ago

Well then I have to use Claude before being able to review the source? Bit of a chicken and egg situation.

I also have to trust its “decompilation” is accurate.

[–] kstenerud 1 hour ago

You're absolutely right! There's no way around this problem — and no amount of creative thought could ever solve it.

All hail the agent!