175K+ publicly-exposed Ollama AI instances discovered
35 points
4 hours ago
| 9 comments
| techradar.com
| HN
gerdesj
2 hours ago
[-]
I'm not sure the "journos" from Techradar are too familiar with how networks ... work.

IPv4 requires an inbound NAT these days to work at all globally, unless you actually have a machine with a globally routable IP. There will probably be a default deny firewall rule too. I do remember the days before NAT ...

IPv6 doesn't require NAT (but prefix translation is available and so is ULA) but again a default deny is likely in force.

You do actually have to try quite hard to expose something to the internets. I know this because I do a lot of it.

The entire article is just a load of buzz words and basically bollocks. Yes it is possible to expose a system on the internet but it is unlikely that you do it by accident. If I was Sead, I'd go easy on the AI generated cobblers and get a real job.

reply
reactordev
1 hour ago
[-]
Fortunately there’s an easy way to check…
reply
meltyness
3 hours ago
[-]
This is a weakness of docker, a bit, I think.

I was rigging this up, myself, and conciscious of the fact that basic docker is "all or none" for container port forwarding because it's for presenting network services, had to dig around with iptables so it'd be similar to binding on localhost.

The use case https://github.com/meltyness/tax-pal

The ollama container is fairly easy to deploy, and supports GPU inference through container toolkit. I'd imagine many of these are docker containers.

e: i stand corrected, apparently -p of `docker run` can have a binding interface stipulated

e2: https://docs.docker.com/engine/containers/run/#exposed-ports which is not in some docs

e3: but it's in the man page ofc

reply
crimsonnoodle58
3 hours ago
[-]
Yes the binding interface can be specified, but the default for -p 11434:11434 is 0.0.0.0.

IMO the default should be 127.0.0.1 and the user should have to explicitly bind to all via -p 0.0.0.0:11434:11434.

reply
meltyness
2 hours ago
[-]
reply
threecheese
3 hours ago
[-]
Out of curiosity, why would you need to wrap the call to an Ollama modelfile in docker? Does the dockerized ollama client provide some benefit, when it’s shelling down to local Ollama instance anyway? (Wrt tax-pal)
reply
meltyness
3 hours ago
[-]
It's more of a distribution thing for me really. I'm basically using docker as a package manager since they otherwise distribute through one of those ad-hoc shell scripts that I'd prefer to avoid accidentally breaking Debian with somehow.

I've built ollama before too, but, I like that I can cleanly rip it out of my system or upgrade it without handing root off to some shell script somewhere I guess.

If anyone's gonna bash up my system it oughta be me

reply
vivzkestrel
50 minutes ago
[-]
- you ll be surprised how many OLLAMA API KEYS [you can find here](https://github.com/search?q=%22OLLAMA_API_KEY%22&type=code&p...) its 2026 and this technique still works. I wonder if github supports regex search
reply
driverdan
32 minutes ago
[-]
I just looked through 2 pages and didn't see any keys, just empty config vars and placeholder values. How many real keys are you actually finding?
reply
adw
3 hours ago
[-]
The tool-calling thing here is overblown.

When you do "tool calling" with an LLM, all you're doing is having the LLM generate output in a particular format you can parse out of the response; it's then your code's responsibility to run the tools (locally) and stick the results back into the conversation.

So that _specific_ part isn't RCE. It's still bad for the nine million other obvious reasons though.

reply
dfajgljsldkjag
3 hours ago
[-]
I see this happen all the time when people just want their new toys to work right away. They copy and paste commands from the internet to open up the connection but they forget to put a lock on the door. It is dangerous that so many people run these programs without understanding the basics of how networks work.
reply
rvz
1 hour ago
[-]
Even better.

We have those who are openly admitting that they have never written / read a line of code and have no idea on what it does and using AI to deploy "AI tools" without knowing how to secure them.

Infosec experts are going to have a great time with collecting lots of money out of this.

reply
FloatArtifact
4 hours ago
[-]
This is a combination problem poor default (listening to all interfaces?) and also IPv6 can be publicly accessible. It's a bit dependent on how this is configured upstream by default, but this is a gotcha compared to IPv4.
reply
chrisjj
4 hours ago
[-]
The article says no, the default is listening to just localhost. Given the instances in question have been deliberately configured to listen on public ports, calling this misconfiguration seems somewhat unjustified.
reply
crimsonnoodle58
3 hours ago
[-]
Not true for their docker instructions which specify -p 11434:11434 instead of -p 127.0.0.1:11434:11434. [1]

Combine that with rootful docker's famous bypass of ufw and you have a publicly exposed ollama, even with a firewall. [2]

[1] https://docs.ollama.com/docker

[2] https://github.com/moby/moby/issues/4737

reply
nxobject
2 hours ago
[-]
Pay for Shodan, folks!
reply
rvz
4 hours ago
[-]
Nevermind. [0] Nothing to see here.

[0] https://news.ycombinator.com/item?id=45116322

reply
cyberax
3 hours ago
[-]
Fun fact! On macOS you can expose privileged ports (<1024) using a regular user account.

But ONLY if you don't bind the listening port to any interface. So you try to create a listening port on localhost (e.g. 127.0.0.1:443) under a non-root account you get a permission error.

Edit: the thing is, you CAN expose "0.0.0.0:443" without root privileges!

reply
kristopolous
2 hours ago
[-]
it's called a privileged port and it's been like this for decades, on every system, ever.

Here's a reference to this "macos feature" from 1995: https://www.w3.org/Daemon/User/Installation/PrivilegedPorts....

reply
Zambyte
54 minutes ago
[-]
reply
vxxzy
2 hours ago
[-]
A feature! Not a bug! Bugs can be undisovered features.
reply
throwaway314155
3 hours ago
[-]
How exactly are the ports "exposed" if they can't be bound to an interface?
reply
Zambyte
59 minutes ago
[-]
Binding to 0.0.0.0 means binding to every interface.
reply