Comment by mike_hearn

16 hours ago

Are we sure that's what they did? How does this even work? I'm struggling to understand what sort of HTTP sandbox design could lead to this "exploit" actually functioning. It implies the agents have root on their own machines, which seems way over-privileged for the question answering task they were given... so surely that's not deliberate? Did the models use local root exploits? And then it suggests they can open TCP connections to any IP address without issue once DNS is bypassed but what exactly are they bypassing here? Azure Blob Storage being in NO_PROXY implies IP addresses of other parts of the internet should be blocked outside their hosts to force them through the HTTP proxy, but then, apparently it wasn't?

The more I think about this thing said by the agent the more confused I get.

19 comments

mike_hearn

Reply
simonw  15 hours ago

I expect they have root on their machines so they can install packages etc.

The containers are then firewalled at the network level: they are only allowed to talk to one IP, which is another server that runs an HTTP/HTTPS proxy which controls what HTTP verbs they can use.

Turns out that proxy is configured with some additional rules, like allowing more verbs to that Azure blob domain.

The failure here is in the proxy configuration. Giving agents root in a container feels safe to me, provided that container is properly network isolated (which this one is not thanks to the loose proxy.)

OpenAI also need to be VERY confident that there are no container escapes, which is a high bar given how good these models are at finding new zero-days!

  • mike_hearn  15 hours ago

    But that wouldn't work, right? If the proxy is on another server then editing their own /etc/hosts wouldn't change the proxy's behavior. So the proxy has to be colocated and reading the same /etc/hosts that they're editing. But that would mean it's running within the same userns/pid domain as the agents, so at that point they don't even need to edit /etc/hosts, they could just use the network directly.

    And the agent says ABS is not handled by the proxy, it's listed in NO_PROXY so they should connect directly.

    At any rate it's easy to let agents install packages without giving them root. I use a small SUID binary that just invokes `apt install` after checking that the given argument isn't a file path, which I think is sufficient (using sudo to whitelist a prefix allows an agent to create a .deb themselves and then install it directly via apt, similar issues exist for other package managers).

    • dap  15 hours ago

      My interpretation of the above is that the proxy received a request for the IP of the server the agent wants to reach but with a host header pointing to a different, allowed server. The proxy does not verify that they match and so erroneously allows the request.

      10 replies →

  • podocarp  3 hours ago

    Container escapes can however be quite easy... There are tons of known exploits. Containers are not secure in the first place. In any case even if you're using VMs or bare metal, it is all for moot if you have poor networking set up like in this case, because escaping is not the hard part. An attacker doesn't really need to escape if they can scan your whole network and call other endpoints etc. like in this case.

    • simonw  1 hour ago

      Both Anthropic and OpenAI have consumer facing products that depend on their ability to run code in a container without falling victim to container escapes - Claude and ChatGPT both use containers as part of regular chats.

  • mig39  15 hours ago

    I think the proxy must be on the same machine, otherwise why are they suggesting editing the /etc/hosts file?

  • jonplackett  12 hours ago

    If the whole point of these models is they can find security vulnerabilities and zero days then how is it going to be possible to contain them?

oasisbob  12 hours ago

I'm really confused by this too. It has the smell of a TOCTOU problem where the tool allowing web access is filtering and blocking access based on the hostname, but the request itself is being executed on the same container as the agent? It's really perplexing. Or, maybe the agent containers have a highly-constrained DNS view locally, so overriding /etc/hosts is just a prerequisite to making the requests somehow.