Live data from Hacker News

I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

coder.com

11–20 of 63 posts

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#11
post #5
post #4

OpenClaw is not insecure because it has ports open to the internet. This is an easily solved problem in one line of code (if indeed it even has that bug, which I don’t think it does). Furthermore you’re probably behind NAT. OpenClaw, as well as the author’s solution, is insecure because it sends the full content of all of your private documents and data to a remote inference API which is logging everything forever (a…

It‘s not just that - but I complete agree on not using a Personal AI assistant with some cloud service LLM provider. Anyway, by interacting with the world, the LLM can be manipulated or even hacked by the data it encounters.

Have you used OpenClaw?

My experience has been that it doesn't take input from the world, unless you explicitly ask it to. But I guess that isn't too crazy, if you ask it to look at a website, maybe the website has a hidden prompt.

I guess that's more of a responsibility of the LLM model in the security model.

That said, I don't think the main dev is serious about security, I've listened to the whole Lex Friedman interview, and he talks about wanting to focus on security, but still dismissing security concerns whenever the arise as coming from 'haters', and there's no recognition of insecurity being possibly an inseparable tradeoff of the functional specifications of the product, I think he thinks of security as something you can slap on a product, which is a very basic misconception I see often in developers that get pwned and managers that think of security as a lever they can turn up or down through budget.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#14
post #4

OpenClaw is not insecure because it has ports open to the internet. This is an easily solved problem in one line of code (if indeed it even has that bug, which I don’t think it does). Furthermore you’re probably behind NAT. OpenClaw, as well as the author’s solution, is insecure because it sends the full content of all of your private documents and data to a remote inference API which is logging everything forever (a…

Yeah, I find the whole concept a bit of a nonstarter until models that I can run on a single somewhat-normal-consumerish machine (e.g. a Mac Studio) with decent capability and speed have appeared. I’m not interested in sending literally everything across the wire to somebody else’s computers, and unless the AI bubble pops and cheap GPUs start raining down on us I’m not interested in building some ridiculous tower/rackmount thing to facilitate it either.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#15
I also started on a similar quest to build an ai agent using LLMs ... and quickly had to throw about 80% of the code away because it was just unreadable and unsecure, based on flawed assumptions the LLM made in its blackbox. So I definitely won't trust something someone vibe-coded run on my computer.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#16

For those interested, you can get the base config Mac Mini (in the US) for $400 from Micro Center [0]. They don’t seem to ship to where I live, but BestBuy was happy to price match in the support chat. Just received mine and planned on experimenting with something like OP this weekend. [0] https://www.microcenter.com/product/688173/apple-mac-mini-mu...

I understand the need for a dedicated box, but any reason you shouldn't just use a server? What would someone recommend for cloud on something like Hetzner?

https://www.hetzner.com/cloud/

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#17
This article fails to mention the bigger security issue with openclaw/anything else like this is prompt injection, not exposed network ports.

Isolating it from incoming requests is better than not, but does nothing to prevent data exfiltration via outgoing requests after being prompted to do so by a malicious email or webpage that it is reading as part of a task you've given it.

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#18

For those interested, you can get the base config Mac Mini (in the US) for $400 from Micro Center [0]. They don’t seem to ship to where I live, but BestBuy was happy to price match in the support chat. Just received mine and planned on experimenting with something like OP this weekend. [0] https://www.microcenter.com/product/688173/apple-mac-mini-mu...

How is it better than a $3/month VPS that you can easily wipe and restart as needed?

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#19
post #11
post #5

Earlier quoted context omitted.

It‘s not just that - but I complete agree on not using a Personal AI assistant with some cloud service LLM provider. Anyway, by interacting with the world, the LLM can be manipulated or even hacked by the data it encounters.

Have you used OpenClaw? My experience has been that it doesn't take input from the world, unless you explicitly ask it to. But I guess that isn't too crazy, if you ask it to look at a website, maybe the website has a hidden prompt. I guess that's more of a responsibility of the LLM model in the security model. That said, I don't think the main dev is serious about security, I've listened to the whole Lex Friedman int…

LLMs famously can't separate data from commands (what you mean by input) - that's one of their core security issues. Check simonw's lethal trifacta. Agreed on all the other points !

Re: I ditched OpenClaw and built a more secure AI agent (Blink and Mac Mini)

#20
post #10

so, ignoring the the fact that you yourself didn't actually write this (based on commit history), and the fact that your claims about better security are dubious at best, the most interesting thing I find about this whole situation is - how did you get this to the hackernews front page so fast? that's the real (not-so) secret sauce here :)

Not saying "ericpaulsen" is a bot, but the account fits the trend I've noticed of other bots on HN recently: they're all accounts created years ago with zero activity and then suddenly a bunch of comments.

Here, "ericpaulsen" was created June 2021, and the only post is in this thread we're in:

https://news.ycombinator.com/threads?id=ericpaulsen

---

Others caught that fit this trend:

https://news.ycombinator.com/item?id=46886875

(This bot made a follow-up: https://news.ycombinator.com/item?id=46901199)

https://news.ycombinator.com/item?id=46886533

Another one 5 days ago that disappeared after being downvoted:

https://news.ycombinator.com/threads?id=Zakodiac

Post reply on HN