Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Setting up OpenClaw on a cloud VM

blog.skypilot.co

Post reply on HN
Print view View original

11–20 of 69 posts

Re: Setting up OpenClaw on a cloud VM

#11

Post by alt187 »

croes wrote: post #3
hopechong wrote: post #2

We've been seeing a lot of people run OpenClaw directly on their main machine, which is a bad idea for a few reasons: it needs broad system access, it's noisy on resources, and if something goes wrong you want a clean blast radius. The obvious answer is "just isolate it," but isolation has real friction. You need to provision a machine, handle SSH keys, configure security groups, and remember to tear things down so y…

That’s only half of the problem. People give OpenClaw access to their online services like mails where it can also do damage. A hardened environment doesn’t prevent those kind of damage

There's no hardening against idiocy.

Re: Setting up OpenClaw on a cloud VM

#13

Post by avoutic »

croes wrote: post #3
hopechong wrote: post #2

We've been seeing a lot of people run OpenClaw directly on their main machine, which is a bad idea for a few reasons: it needs broad system access, it's noisy on resources, and if something goes wrong you want a clean blast radius. The obvious answer is "just isolate it," but isolation has real friction. You need to provision a machine, handle SSH keys, configure security groups, and remember to tear things down so y…

That’s only half of the problem. People give OpenClaw access to their online services like mails where it can also do damage. A hardened environment doesn’t prevent those kind of damage

It does, of you use WardGate [1] and only allow read and archive access and only delete access on your inbox but nothing else for instance.

1 https://github.com/wardgate/wardgate

Re: Setting up OpenClaw on a cloud VM

#14

Post by seniorThrowaway »

It's really not that hard to run them in docker. Can give them a nestybox (with a little work) sidecar so they can run docker-in-docker. As far as permissions, the only mental model that makes sense to me is treating them like actual people. Bound their permissions in the other systems not on their own machines, basically zero trust. For instance for email, most mail apps have had delegated permissions for a while, executives use it to have their assistants read and write their mail. That's what is needed with these too.

Re: Setting up OpenClaw on a cloud VM

#15

Post by avoutic »

ziml77 wrote: post #9
croes wrote: post #3

Earlier quoted context omitted.

That’s only half of the problem. People give OpenClaw access to their online services like mails where it can also do damage. A hardened environment doesn’t prevent those kind of damage

As people have pointed out in other threads, you don't even need access to these services to cause problems. As long as the AI can send any bytes out, it can leak information. Like you may think of an HTTP GET as read-only, but you can pack any data you want into the URL or headers.

In the end it will all be about separation of duty between agents in a larger team and isolating the ones that need more access to your private stuff.

Wardgate acts like a drop in replacement for curl with full access control at the url / method / content level, so you can allow specific curl access to specific APIs but prevent all other outbound connections. That's what I use for my PA agent. She's very limited and can't access the open internet. Doesn't need it either

Re: Setting up OpenClaw on a cloud VM

#16

Post by Spivak »

alienbaby wrote: post #12

Put it in a box and then give it read write access to all your valuable data. That'll do it....

Because the VM isn't there to protect your data, it's to give the AI a space where it can do things that would be annoying or cause breakages on your own machine. It also gives you an easy save/restore mechanism.

Re: Setting up OpenClaw on a cloud VM

#17

Post by leptons »

ziml77 wrote: post #9
croes wrote: post #3

Earlier quoted context omitted.

That’s only half of the problem. People give OpenClaw access to their online services like mails where it can also do damage. A hardened environment doesn’t prevent those kind of damage

As people have pointed out in other threads, you don't even need access to these services to cause problems. As long as the AI can send any bytes out, it can leak information. Like you may think of an HTTP GET as read-only, but you can pack any data you want into the URL or headers.

You can also stuff data into a GET request body, I've seen some devs do it and I related my disapproval about it.

Re: Setting up OpenClaw on a cloud VM

#18

Post by stronglikedan »

LostAndSmelly wrote: post #5

Your AI should not be in a position to submit a resignation email or send a text to your partner asking for a divorce.

As long as the email or text includes the disclaimer "generated with the assistance of artificial intelligence" then you should be fine.
Post reply on HN