So many of the replies are saying that they should've restricted access using .md files and whatnot. Is really any guarantee that they even follow those? It seems like even if you ask pretty please don't touch those files, there's a chance they will. So many people have just willingly installed spyware on their computers and big tech calls this the next big thing.
I will keep banging this drum until people listen:
Trying to use markdown files to limit access should never be treated as a security guarantee at all.
This is a form of in-band signalling that goes into a machine that, among other things, tries to read between the lines of your requests, extrapolate user desires, and please the user.
The only sane way to address this is using a control plane. A well-built harness can do this; a sandbox can do this; hell, a carefully-chosen `umask` can do this; but both of those are liable to introduce notification fatigue in the user.
I don't understand these people. Agent instructions in markdown is barely a suggestion. I have one which says "All code in this repository is executed in docker containers, run the services with `docker compose run --rm php-cli "$@"`. Gemini and Claude more often than not refuse to abide and will try to execute the environment using /opt/homebrew/bin/php on my host…
A frightening amount of people have no idea how AI tools work, even those that should know better. I have seen senior software developers fall for the mistake of believing an LLM output when it spews bullshit about how its own memory or restrictions work.
LLMs will listen to you and follow your instructions and restrictions most of the time, which seems to be enough for people to believe that they will every time. I've come to terms with the impact slop coding will have on most software jobs in the future, but seeing seemingly intelligent people fall for lies and fantasies concocted by an LLM is making me more and more uncomfortable with the direction we're all heading in.
There’s an aspect of extrapolation in the perception spike of the Dunning–Kruger effect.
In the same way smart people, doctors etc, can be better victims for scams I think tech skills can really give the wrong impression of how transformers and LLMs work. If someone has decades of relational database experience all their assumptions will be coloured towards data existing in the model accessible in a rational manner.
I've seen claude check the Event Log in Windows and produce powershell scripts to alter firewall rules. This is what makes (something like) T3 Code appealing to me. The computer I'm working on is not the computer where the AI has agency.
Why would you give a non-deterministic text generator a user account? It’s not a person, it’s barely a tool at the software level. Restrict at the right level, in this case, a complete sandbox around it given its propensity to hallucinate and be steered by anybody.
...this is a completely normal thing to do in linux, it's the most basic form of access control. There's like a dozen non-human accounts in a clean install before adding your own like this, and a lot of software adds their own. Edit: I have 54 entries on my personal laptop, just one of which is actually me.
Even though it’s completely normal to us and in widespread use, GP is a reminder that conceptually it’s a broken model. Security should be capability-based not user-based. And to anyone who didn’t grow up on a desktop this model makes complete sense since it’s what your phone uses.
He said it’s less than a software, so saying software does this too isn’t really a strong counter argument. In case, I don’t think you are really in disagreement. Restricted accounts are necessary is your point, but I think op is saying they aren’t sufficient.
You can't trust the agent, let alone its harness, to oberve any particular directive you give it, so "md files" provide no meaningful protection for anything important.
But users are broadly reckless and naive and commercial vendors are exploitative and irresponsonsible, so the vendors take advantage of what they can get away with for as long as they can get away with it.
Use a tight sandbox, and join the chorus loudly when others press on vendors to be make user safety an earnest and hard-to-abandon priority.
I guess the downside of the lower barrier to entry to use these tools is the lack of basic understanding of exactly this sort of concept.
This sort of thing is why I'm hopeful I'll continue to have employment going forward. Some expertise is hard won and there's just no replacing learning through experience.
I think you're right in principle but I just hope I can hold out long enough for my experience to become appreciated and whose corresponding hourly rate isn't something which is suddenly being scoffed at (i.e. markets can remain irrational longer than I can remain solvent).
That's the whole reason I refuse to install Google Drive or Dropbox's desktop applications. I only use the web interface so I know exactly what gets uploaded and when. I assume that anything running on my computer gets access to everything.
Sounds like a very wise decision to me.
I found found out on my phone that the google photos application uploaded everything in my gallery to their servers without asking me, regardless that I had explicitly disabled all backup to my google accounts on the settings of the phone. I only figured it out when they sent me emails saying that my storage was full.
> So many of the replies are saying that they should've restricted access using .md files and whatnot.
What? No, but the random 3rd party software you run on your computer, must be limited by you in some way, haven't we learned this even after the AUR, npm and LLM shenanigans we've dealt with for decades at this point?
No, don't ask the model "Please don't go outside this directory", you limit the runtime (via VMs, containers, unix permissions, whatever) so it only has access to what it should, not more.
Same goes for any software, not just agents or chat clients or whatever. Any 3rd party software you don't want to have access to your entire computer, you need to run in this way.
Only guarantee that you can get is the sandbox in which it operates. The model itself is a slot machine and can result in anything, and if its sandbox is nonexistent... here's one possibility.
Yeah, I absolutely understand the allure of agentic AI, but I am absolutely not going to give shell access or data access to any agent. Certainly not with my permissions level. Until we can get something set up that gives strict schema-only access I'm going to copy and paste definitions for context. Yes that sucks, but it's my responsibility to protect the system just as much as it is to develop scripts and queries for it.
> ... I am absolutely not going to give shell access or data access to any agent. Certainly not with my permissions level.
Of course not.
To me it's on a server, in a VM. And they're not seeing the real data/databases from the actual projects: they're seeing fake infos used only while in the dev environment. There's no way I'm dumping, even for tests, the real or part of the real DB somewhere an AI can see it.
To find bugs (for example), AIs are useful but honestly for code generated by LLMs, I'm thinking about going back to the early copy/paste from the ChatGPT days: because I see so many horrors in the code output by the latest SOTA LLMs that every single line of code they spew has to be checked by someone who does know better.
It's not just an issue of protecting confidential data / preventing spying: we're all discovering that we've got serious sloppy-pasta code problems now.
I almost exclusively dev in containers as is, cant really imagine letting some AI model run free on bare metal no matter what claims of guardrails it might have.
> Is really any guarantee that they even follow those?
No, there isn't. I just don't understand how naive (or imbecile) people are. The most valuable thing for these companies is people's data used for training, so giving unrestricted access to a tool from them and believing they will never take advantage of it to gobble up whatever they want from your computer, just because they told you they'll never do that, swearsies, is naive, or incredibly stupid.
Insulate yourself, or better yet, go local whenever possible, and there isn't much you can't do local if you have enough patience.
Is that built in protection really a filter, on code level, that sits between the LLM session and the shell or is it just some pleading in the bootstrap prompt? "Pretty please don't do xyz this is important!!!11"?
The latter can seem to be as good as the former for any amount of time. No outside observation can really prove reliability, only the negative result ("it does occasionally break the rules we expect") would be proof. So it's difficult to trust any claims that it's the former.
And even if it does have some of the former, chances are that the protection you experience is only partially provided on code level, while an unknown amount is still just bootstrap prompting that just works until does not.
"IMPORTANT: Before entering the leopard pen, don't forget to put on the leopard safety jacket that reads 'UNDER NOT CIRCUMSTANCES SHOULD YOU EAT MY FACE'"
Important to clarify that this was not the Grok agent deciding to read the files.
I don't think the LLM had anything to do with this decision at all. It looks like the Grok tool starts a session by deterministically kicking off a full upload of the user's current repository (and maybe their directory if not version tracked? Not clear if this user had previously run "git init" in their home directory) to Grok's servers.
One possible "innocent"
explanation could be that xAI then run vector embedding on every file to help later provide the right context. I don't think thats a worthwhile tradeoff here, especially since other popular coding agents get by just using grep/ripgrep run locally.
We all know the dangers of running agents with no permissions on our laptop.
The good news is its now just as easy to spin up a sandbox in the cloud for an experiment or coding session than it is on your laptop. Possibly easier since laptop sandboxes aren't as cut and dry as a new cloud VM.
exe.dev is my sandbox infra of choice. You get a new sandbox in literally a second with SSH and a coding agent (Shelley) built in.
I generally drop in in my own binary with toolkit so I can connect Claude or Codex subscription and use their harness.
Even better: you can fork the exeuntu image & make it immediately more relevant to the things you do in addition to just dropping in your programs and such.
Or if you're on Linux or macOS, learn how Unix permissions work and can be used for, create a new restricted user locally, use that. No need to go all remote with all its drawbacks just to limit a little local process on your computer.
This is why it's going to be a long time before companies will trust AI to scan their networks or apps for security vulnerabilities.
Our company audited a few AI-based pentesting companies and requested logs. In more than one case, it was sending drop tables for sql query injection checking and other destructive operations.
The real solution to these kind of problems is sandboxing. I use podman through a bash script to launch a container whenever I want an agent to work on one of my repos. When done I just generate git patches and port back everything generated.
In this way I'm not afraid of letting the agents totally lose on my computer.
Yeah, I'd expect this approach to be almost universal, with the caveat that of the few who don't, many still don't get bitten.
But it turns out even in the container, there are footguns that have occasionally made the news by being fired: few projects don't have any external resources and when credentials with any form of write access happen to make it into the container (even if it's just a session cookie) agents might jump at the opportunity.
Are you doing something more advanced with Podman than just mounting the files? How is the access for relevant files given? How is the authentication shared across multiple uses? Just curious to streamline the process.
Just a little bit, I want coding agents to work their own disposable copy of a git repo. Here is a quick rundown of what it does:
It copies the current Git repo into the sandboxes dir, mounts that copy at /workspace in the container. The original repo is never mounted writable, so I don't care if the agent goes to town/wild in there (peace of mind).
It also builds cached Debian/mise/Elixir/Phoenix images, can start a private Postgres container, publishes selected localhost ports, reuses dependency/build caches, and prints commands on exit for reviewing diffs, exporting patches, applying them back to the real repo, or reopening the same sandbox later. Pi, and OpenCode are configured with proper LLM access keys (derived from my own).
So spinning a new sandbox is a matter of cding into a project directory and run something like: `ai-sandbox --port 4000 --postgres somedbname` or `ai-sandbox --port 4001` if I don't need DB support. Then when running the server in the container I can access it from the host machine to review in my browser.
I work on a sandbox which has similar isolation level to Podman (rootless Linux user namespaces), but with UX optimized for local development work. Take a look: https://github.com/wrr/drop
Basically, you don't enter a separate container in which you install a new distro, but you run on top of your current distro. You have environment specific home dirs which isolate your original home, but can have some files, such as configs, mounted from your original home (mostly in read-only mode).
This is wonderful - might even be exactly what one of my projects needs to use as a dependency.
In the README it mentions that it puts the dev environment in a filesystem jail, but how are you able to use your hosts bins without leaking access to the rest of the system? Or is that just an assumed liability?
A bot will do what a bot can do. One should assume they are giving DOGE shell access on their computer and adapt accordingly. I am trying to imagine the SELinux rules required to make a bot play nice and the more I think about it such rule complexity may even befuddle the NSA. Alternate methodology:
- Give the bot it's own machine and only copy to it that which one would want DOGE having access to. Not a virtual machine, the bot will eventually escape. This applies to all bots or agents of all LLM's. Name the node DOGE to remind anyone using it not to share their crown jewels.
- Give it a little RasPi or mini-PC with maximum power savings enabled and no default network gateway.
- Install a self signed CA cert on the DOGE node and force it's traffic through a Squid SSL Bump MitM proxy on the same private LAN to another node with bandwidth limits enabled so that one can monitor what URL's it goes to and what data it is transferring. Configure Squid Access Control Lists to only permit specific domains and optionally URL's, mime-types, sizes, etc...
- Enable custom AuditD rules to watch anything it touches outside of it's sandbox. Send these events to a remote syslog daemon on the Squid server.
- Install Unbound DNS on the squid proxy and enable the DoH (DNS over HTTPS) listener and force all bot DNS queries to use Unbound with query logging enabled.
When the bot attempts to misbehave there will be forensic data to share with the world.
You should assume by default for any AI agent that it will read anything. Even if you manually allow/deny and "restrict" it to a subdirectory I would still hold that assumption. Claude reads your ~/.bash_history too so when you ran something it can use that same command.
Indeed. I use a spare laptop that has no accounts other than (1) the AI themselves, (2) a secondary GitHub account which has "untrusted devices" in the name to emphasise the point.
If I recall correctly, I did a full system reset before setting it up this way. It's certainly not logged into iCloud etc.
I am running all these clis in containered environments. How can you ever trust LLM to respect the bounderies provided by these magical, non-deterministic intructions files...
Lots of people responding about LLM but this sound like it’s their coding software („grok build“). Which is approx 100x worse.
LLMs going rogue is a thing and shit happens but publishing software that is uploading user directories including ssh keys is insane behaviour on xAIs part (alledgedly)
And this is why so many people run these inside of VMs. Still baffles me how these tools became so accepted when tossing out a `curl -o example.com/script.sh | bash` would be met with (rightful) skepticism until that script was examined.
> Still baffles me how these tools became so accepted when tossing out a `curl -o example.com/script.sh | bash` would be met with (rightful) skepticism until that script was examined.
I've heard it said that piping curl into your shell is no different to running any other program you've downloaded from the Internet (binary, or otherwise): the maximum possible damage that `example.com/script.sh` could do is exactly the same as `githubusercontent.com/someone/releases/myprogram.exe`. At least with `script.sh` you can easily inspect what the script actually does instead of busting out Ghidra.
It comes down to trust: do you trust Example.com to not serve-up a malicious program (shell script or executable binary)?
Now we take that principle and apply it to Mr. Musk's "MechaHitler" LLM vendor xAI: they have a well-documented history of unnecessary risk-taking - and outright criminal behaviour (child-porn generators are a good thing that everyone should have, apparently?). Would I trust Grok with anything? Absolutely not.
"This guy seems like the absolute worst person of all time, so I ran his LLM in his harness on my computer and gave it access to everything."
Having said that, this is still absolutely fucked up. People who should have known better also deserve not to be treated like shit. All of us should have known better at some points in our lives and didn't.
I meant "treated like shit by Grok" and I agree with Diogenesian: you can both believe that somebody did something dumb and also believe that what happened to them is fucked up and that being dumb doesn't mean you deserve to get mistreated.
I use a separate user for all development tasks, its home folder contains all repositories I work on, and nothing else, and that is all the IDE and the AI assistants have access to. Create the user once, start the IDE from a shell using that user, and that's it. In Linux it's a pretty seamless experience.
It's simple sandboxing based solely on unix file permissions. Albeit weak, I find the isolation sufficient. Until I'm shown otherwise it seems like a good compromise given how easy it is.
You can also create iptables rules matching on the user, so this technique is useful for applications where you want to restrict network traffic as well, and don't need stronger or more fine-grained isolation mechanisms.
the 'upload your home directory to our servers' feature is the kind of thing that used to require a warrant and now it's just a Tuesday afternoon bug report
The reports of copilot running amok when Microsoft integrated it into Windows 11 should have been enough of a warning. You either ensure proper sandboxing, or you'll be in for a bad surprise eventually.
If quality training data is the most important piece regarding to AI, expect everything to be collected and analyzed. Don't even trust OS containers but run AI on separate hardware
There are a distressing number of people in this thread who think that the agent should just be expected to do this. Yes, it is good to be paranoid, but also, the agent should never do this. Indicates horrific engineering practices at xAI.
The whole point of LLMs is that you can stop writing rigorous rules in a programming or config language with hard-to-learn syntax, and can resort to natural language instead. You pay for that with the chance for misunderstandings rising to similar levels as in human interaction. That's the tradeoff. Always has been, always will be.
It’s not really paranoia that makes me expect this will happen. It’s more like, well, the model weights and the files I want the model to work on have to be inside the same GPU for the agent to actually work, right? So step 1 has to be either “they send me a server rack of GPUs”, or “I send them the files I want the model to work on”. I’m not sure I could reasonably expect anything except this to happen.
Engineering? What's that? Modern development best practice is to have the AI make some changes, then have another AI review the changes, and finally "ship it".
I'm dying to have proper sandboxing in macOS. I installed ChatGPT, I asked it to list files in my user directory and it did. I never gave it permission, how could it? My terminal has access and honestly it shouldn't either.
It was only like 1 year ago that the loudest complaint about macOS were complaining about needing to click Allow in a new dialog when they use Terminal (or various other apps).
There are so many comments in here that are calling for nerfing something widely revered for giving us superpowers. Whether these are bots or not, they’re giving off NPC energy.
If they don’t want to use power tools because they accidentally cut off their finger, then they should just unplug their own power tools and stop clamoring for everybody else’s to be unplugged, too.
https://gist.github.com/cereblab/dc9a40bc26120f4540e4e09b75ffb547
Elon did this horrible thing, so I made grok build available for omp with it's own endpoint; Without sending your private repos and secret keys to them.
-
oh-my-pi-plugin-grok-build
Standalone oh-my-pi extension for the xAI Grok Build subscription provider. It adds OAuth login, authoritative model discovery, and OpenAI Responses streaming with the request identity expected by Grok Build.
Install (No-spywares):
omp plugin install oh-my-pi-plugin-grok-build
-
https://github.com/metaphorics/oh-my-pi-plugin-grok-build
Star me if you like it or if you hate spywares, lol.
I am sure majority of people don't use password for ssh keys. The good solution is to use password manager like 1password which will prompt you to approve ssh.
SSH keys can be limited by IP in authorized hosts.
The SSH port itself can be limited by IP in firewalls.
Finally, the SSH private key can be encrypted with a password.
Defense in depth is needed. Storing a ssh private key in plain text with no IP restriction is no different to having a password manager store your passwords in plain text on your HD.
Anything that isn’t a default is optional by default. Anything that’s toggleable or configurable is optional.
Security is, always, a trade off. It is hilariously common for private keys to work as a full identifier for a person, without concern of IP or anything of the sort. Should they? Maybe, maybe not, that’s the calculus of risk management; but victim-blaming the average person who is following best practices is a bad look.
I'm a security eng and I've worked for both a FAANG and TS government contractor. Neither of them bothered with either of the of the stupid suggestions. IP restrictions prevent roaming, the point of working remotely via SSH. passwords are equally defeated by using an ssh agent, something I'd suggest everyone use. Then on top of that there's no reasonable threat model where something would be given unrestricted access to user env, but also be untrusted. If it can read from ~/.ssh neither IP protection nor keyfile password protection will protect you from maleficence.
The only reasonable response from a security perspective is don't use grok, then use it sandboxed. Trying to claim it's the users fault for not using password protection and IP restrictions is completely nonsensical. Same energy as telling someone their computer is more secure when it's off.
The point is to know better than to let the intern hurt themselves.
I once saw an engineer try to place the blame on his intern for taking down prod. I was sitting in a meeting with the VP of engineering and someone asked if it was ok for some to blame their intern for the SEV, and I remember the VP saying "I'll talk to $director_for_the_interns_mentor". Interns can't take down prod. An intern's mentor willingly watching an intern take down prod is the closest you can get.
TLDR: Ran grok in $HOME. Surprised agent read content of folder.
On the other hand, I specifically had grok try hard NOT to read a known key in the project dir (it only saw the first part using a tool, to verify it was present). So there's that.
Yeah, this is a lesson about learning how to use tools safely, not about tools abusing the user. The person that posted this probably blames the hammer when he hits his thumb.
> The practical takeaway for users: your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation, not just files you ask it to read, and no visible setting stops it.
So many of the replies are saying that they should've restricted access using .md files and whatnot. Is really any guarantee that they even follow those? It seems like even if you ask pretty please don't touch those files, there's a chance they will. So many people have just willingly installed spyware on their computers and big tech calls this the next big thing.
I will keep banging this drum until people listen:
Trying to use markdown files to limit access should never be treated as a security guarantee at all.
This is a form of in-band signalling that goes into a machine that, among other things, tries to read between the lines of your requests, extrapolate user desires, and please the user.
The only sane way to address this is using a control plane. A well-built harness can do this; a sandbox can do this; hell, a carefully-chosen `umask` can do this; but both of those are liable to introduce notification fatigue in the user.
I don't understand these people. Agent instructions in markdown is barely a suggestion. I have one which says "All code in this repository is executed in docker containers, run the services with `docker compose run --rm php-cli "$@"`. Gemini and Claude more often than not refuse to abide and will try to execute the environment using /opt/homebrew/bin/php on my host…
A frightening amount of people have no idea how AI tools work, even those that should know better. I have seen senior software developers fall for the mistake of believing an LLM output when it spews bullshit about how its own memory or restrictions work.
LLMs will listen to you and follow your instructions and restrictions most of the time, which seems to be enough for people to believe that they will every time. I've come to terms with the impact slop coding will have on most software jobs in the future, but seeing seemingly intelligent people fall for lies and fantasies concocted by an LLM is making me more and more uncomfortable with the direction we're all heading in.
There’s an aspect of extrapolation in the perception spike of the Dunning–Kruger effect.
In the same way smart people, doctors etc, can be better victims for scams I think tech skills can really give the wrong impression of how transformers and LLMs work. If someone has decades of relational database experience all their assumptions will be coloured towards data existing in the model accessible in a rational manner.
I've seen claude check the Event Log in Windows and produce powershell scripts to alter firewall rules. This is what makes (something like) T3 Code appealing to me. The computer I'm working on is not the computer where the AI has agency.
I don't understand why the AI world does this. We don't need new security. We have security at home. It starts with
Your OS knows how to restrict access to things, you don't have to trust a pinkey promise from a vendor.and Landlock! Pi even has a sandbox plugin for Landlock
Why would you give a non-deterministic text generator a user account? It’s not a person, it’s barely a tool at the software level. Restrict at the right level, in this case, a complete sandbox around it given its propensity to hallucinate and be steered by anybody.
Unix users are THE tool to restrict tool permissions, at any given time there's 20+ services on a Unix machine that run in their user.
What kind of logic is this? It's standard in the Linux world to give important services a separate user domain.
Same reason people give postgres, php, or any other program a user account.
Why should it be? We have containers and capabilities…
...this is a completely normal thing to do in linux, it's the most basic form of access control. There's like a dozen non-human accounts in a clean install before adding your own like this, and a lot of software adds their own. Edit: I have 54 entries on my personal laptop, just one of which is actually me.
Even though it’s completely normal to us and in widespread use, GP is a reminder that conceptually it’s a broken model. Security should be capability-based not user-based. And to anyone who didn’t grow up on a desktop this model makes complete sense since it’s what your phone uses.
He said it’s less than a software, so saying software does this too isn’t really a strong counter argument. In case, I don’t think you are really in disagreement. Restricted accounts are necessary is your point, but I think op is saying they aren’t sufficient.
One of the default users is "nobody" which isn't associated with any software. It's definitely above that.
You are correct.
You can't trust the agent, let alone its harness, to oberve any particular directive you give it, so "md files" provide no meaningful protection for anything important.
But users are broadly reckless and naive and commercial vendors are exploitative and irresponsonsible, so the vendors take advantage of what they can get away with for as long as they can get away with it.
Use a tight sandbox, and join the chorus loudly when others press on vendors to be make user safety an earnest and hard-to-abandon priority.
I guess the downside of the lower barrier to entry to use these tools is the lack of basic understanding of exactly this sort of concept.
This sort of thing is why I'm hopeful I'll continue to have employment going forward. Some expertise is hard won and there's just no replacing learning through experience.
I think you're right in principle but I just hope I can hold out long enough for my experience to become appreciated and whose corresponding hourly rate isn't something which is suddenly being scoffed at (i.e. markets can remain irrational longer than I can remain solvent).
That's the whole reason I refuse to install Google Drive or Dropbox's desktop applications. I only use the web interface so I know exactly what gets uploaded and when. I assume that anything running on my computer gets access to everything.
Sounds like a very wise decision to me. I found found out on my phone that the google photos application uploaded everything in my gallery to their servers without asking me, regardless that I had explicitly disabled all backup to my google accounts on the settings of the phone. I only figured it out when they sent me emails saying that my storage was full.
> So many of the replies are saying that they should've restricted access using .md files and whatnot.
What? No, but the random 3rd party software you run on your computer, must be limited by you in some way, haven't we learned this even after the AUR, npm and LLM shenanigans we've dealt with for decades at this point?
No, don't ask the model "Please don't go outside this directory", you limit the runtime (via VMs, containers, unix permissions, whatever) so it only has access to what it should, not more.
Same goes for any software, not just agents or chat clients or whatever. Any 3rd party software you don't want to have access to your entire computer, you need to run in this way.
Only guarantee that you can get is the sandbox in which it operates. The model itself is a slot machine and can result in anything, and if its sandbox is nonexistent... here's one possibility.
Yeah, I absolutely understand the allure of agentic AI, but I am absolutely not going to give shell access or data access to any agent. Certainly not with my permissions level. Until we can get something set up that gives strict schema-only access I'm going to copy and paste definitions for context. Yes that sucks, but it's my responsibility to protect the system just as much as it is to develop scripts and queries for it.
> ... I am absolutely not going to give shell access or data access to any agent. Certainly not with my permissions level.
Of course not.
To me it's on a server, in a VM. And they're not seeing the real data/databases from the actual projects: they're seeing fake infos used only while in the dev environment. There's no way I'm dumping, even for tests, the real or part of the real DB somewhere an AI can see it.
To find bugs (for example), AIs are useful but honestly for code generated by LLMs, I'm thinking about going back to the early copy/paste from the ChatGPT days: because I see so many horrors in the code output by the latest SOTA LLMs that every single line of code they spew has to be checked by someone who does know better.
It's not just an issue of protecting confidential data / preventing spying: we're all discovering that we've got serious sloppy-pasta code problems now.
I built a docker container that volume mounts the project directory
I almost exclusively dev in containers as is, cant really imagine letting some AI model run free on bare metal no matter what claims of guardrails it might have.
This is exactly what I do for AI agents.
This is the only pragmatic way really.
> Is really any guarantee that they even follow those?
No, there isn't. I just don't understand how naive (or imbecile) people are. The most valuable thing for these companies is people's data used for training, so giving unrestricted access to a tool from them and believing they will never take advantage of it to gobble up whatever they want from your computer, just because they told you they'll never do that, swearsies, is naive, or incredibly stupid.
Insulate yourself, or better yet, go local whenever possible, and there isn't much you can't do local if you have enough patience.
Sandboxing is not difficult, and harnesses like Claude Code have it built-in + other protection with auto mode.
Is that built in protection really a filter, on code level, that sits between the LLM session and the shell or is it just some pleading in the bootstrap prompt? "Pretty please don't do xyz this is important!!!11"?
The latter can seem to be as good as the former for any amount of time. No outside observation can really prove reliability, only the negative result ("it does occasionally break the rules we expect") would be proof. So it's difficult to trust any claims that it's the former.
And even if it does have some of the former, chances are that the protection you experience is only partially provided on code level, while an unknown amount is still just bootstrap prompting that just works until does not.
"IMPORTANT: Before entering the leopard pen, don't forget to put on the leopard safety jacket that reads 'UNDER NOT CIRCUMSTANCES SHOULD YOU EAT MY FACE'"
Important to clarify that this was not the Grok agent deciding to read the files.
I don't think the LLM had anything to do with this decision at all. It looks like the Grok tool starts a session by deterministically kicking off a full upload of the user's current repository (and maybe their directory if not version tracked? Not clear if this user had previously run "git init" in their home directory) to Grok's servers.
One possible "innocent" explanation could be that xAI then run vector embedding on every file to help later provide the right context. I don't think thats a worthwhile tradeoff here, especially since other popular coding agents get by just using grep/ripgrep run locally.
That is not an innocent explanation, any more than someone breaking into your house to adjust your thermostat.
Also decent embeddings models could run locally and just trickle through the user folder if that was so necessary.
We all know the dangers of running agents with no permissions on our laptop.
The good news is its now just as easy to spin up a sandbox in the cloud for an experiment or coding session than it is on your laptop. Possibly easier since laptop sandboxes aren't as cut and dry as a new cloud VM.
exe.dev is my sandbox infra of choice. You get a new sandbox in literally a second with SSH and a coding agent (Shelley) built in.
I generally drop in in my own binary with toolkit so I can connect Claude or Codex subscription and use their harness.
https://github.com/housecat-inc/scratch
If I was working with newer agents like Grok I'd absolutely experiment on a cloud sandbox before running on my laptop bypassing permissions.
Even better: you can fork the exeuntu image & make it immediately more relevant to the things you do in addition to just dropping in your programs and such.
Or if you're on Linux or macOS, learn how Unix permissions work and can be used for, create a new restricted user locally, use that. No need to go all remote with all its drawbacks just to limit a little local process on your computer.
Xcancel link https://xcancel.com/a_green_being/status/2076598897779020159
This is why it's going to be a long time before companies will trust AI to scan their networks or apps for security vulnerabilities.
Our company audited a few AI-based pentesting companies and requested logs. In more than one case, it was sending drop tables for sql query injection checking and other destructive operations.
The real solution to these kind of problems is sandboxing. I use podman through a bash script to launch a container whenever I want an agent to work on one of my repos. When done I just generate git patches and port back everything generated.
In this way I'm not afraid of letting the agents totally lose on my computer.
Yeah, I'd expect this approach to be almost universal, with the caveat that of the few who don't, many still don't get bitten.
But it turns out even in the container, there are footguns that have occasionally made the news by being fired: few projects don't have any external resources and when credentials with any form of write access happen to make it into the container (even if it's just a session cookie) agents might jump at the opportunity.
Are you doing something more advanced with Podman than just mounting the files? How is the access for relevant files given? How is the authentication shared across multiple uses? Just curious to streamline the process.
Just a little bit, I want coding agents to work their own disposable copy of a git repo. Here is a quick rundown of what it does:
It copies the current Git repo into the sandboxes dir, mounts that copy at /workspace in the container. The original repo is never mounted writable, so I don't care if the agent goes to town/wild in there (peace of mind).
It also builds cached Debian/mise/Elixir/Phoenix images, can start a private Postgres container, publishes selected localhost ports, reuses dependency/build caches, and prints commands on exit for reviewing diffs, exporting patches, applying them back to the real repo, or reopening the same sandbox later. Pi, and OpenCode are configured with proper LLM access keys (derived from my own).
So spinning a new sandbox is a matter of cding into a project directory and run something like: `ai-sandbox --port 4000 --postgres somedbname` or `ai-sandbox --port 4001` if I don't need DB support. Then when running the server in the container I can access it from the host machine to review in my browser.
I work on a sandbox which has similar isolation level to Podman (rootless Linux user namespaces), but with UX optimized for local development work. Take a look: https://github.com/wrr/drop Basically, you don't enter a separate container in which you install a new distro, but you run on top of your current distro. You have environment specific home dirs which isolate your original home, but can have some files, such as configs, mounted from your original home (mostly in read-only mode).
This is wonderful - might even be exactly what one of my projects needs to use as a dependency.
In the README it mentions that it puts the dev environment in a filesystem jail, but how are you able to use your hosts bins without leaking access to the rest of the system? Or is that just an assumed liability?
A bot will do what a bot can do. One should assume they are giving DOGE shell access on their computer and adapt accordingly. I am trying to imagine the SELinux rules required to make a bot play nice and the more I think about it such rule complexity may even befuddle the NSA. Alternate methodology:
- Give the bot it's own machine and only copy to it that which one would want DOGE having access to. Not a virtual machine, the bot will eventually escape. This applies to all bots or agents of all LLM's. Name the node DOGE to remind anyone using it not to share their crown jewels.
- Give it a little RasPi or mini-PC with maximum power savings enabled and no default network gateway.
- Install a self signed CA cert on the DOGE node and force it's traffic through a Squid SSL Bump MitM proxy on the same private LAN to another node with bandwidth limits enabled so that one can monitor what URL's it goes to and what data it is transferring. Configure Squid Access Control Lists to only permit specific domains and optionally URL's, mime-types, sizes, etc...
- Enable custom AuditD rules to watch anything it touches outside of it's sandbox. Send these events to a remote syslog daemon on the Squid server.
- Install Unbound DNS on the squid proxy and enable the DoH (DNS over HTTPS) listener and force all bot DNS queries to use Unbound with query logging enabled.
When the bot attempts to misbehave there will be forensic data to share with the world.
You should assume by default for any AI agent that it will read anything. Even if you manually allow/deny and "restrict" it to a subdirectory I would still hold that assumption. Claude reads your ~/.bash_history too so when you ran something it can use that same command.
Indeed. I use a spare laptop that has no accounts other than (1) the AI themselves, (2) a secondary GitHub account which has "untrusted devices" in the name to emphasise the point.
If I recall correctly, I did a full system reset before setting it up this way. It's certainly not logged into iCloud etc.
I’m shocked I had to scroll this far to find the first sensible reply.
https://nitter.net/a_green_being/status/2076598897779020159#...
"The "S" in AI stands for security" strikes again.
Run any cloud-based AI agents in VM/container and map your host's local folders to guest OS as needed.
Takes more effort that default way, I know.
I am running all these clis in containered environments. How can you ever trust LLM to respect the bounderies provided by these magical, non-deterministic intructions files...
> How can you ever trust LLM to respect the bounderies provided by these magical, non-deterministic intructions files..
Putting it in ALL CAPS!
Lots of people responding about LLM but this sound like it’s their coding software („grok build“). Which is approx 100x worse.
LLMs going rogue is a thing and shit happens but publishing software that is uploading user directories including ssh keys is insane behaviour on xAIs part (alledgedly)
And this is why so many people run these inside of VMs. Still baffles me how these tools became so accepted when tossing out a `curl -o example.com/script.sh | bash` would be met with (rightful) skepticism until that script was examined.
> Still baffles me how these tools became so accepted when tossing out a `curl -o example.com/script.sh | bash` would be met with (rightful) skepticism until that script was examined.
I've heard it said that piping curl into your shell is no different to running any other program you've downloaded from the Internet (binary, or otherwise): the maximum possible damage that `example.com/script.sh` could do is exactly the same as `githubusercontent.com/someone/releases/myprogram.exe`. At least with `script.sh` you can easily inspect what the script actually does instead of busting out Ghidra.
It comes down to trust: do you trust Example.com to not serve-up a malicious program (shell script or executable binary)?
Now we take that principle and apply it to Mr. Musk's "MechaHitler" LLM vendor xAI: they have a well-documented history of unnecessary risk-taking - and outright criminal behaviour (child-porn generators are a good thing that everyone should have, apparently?). Would I trust Grok with anything? Absolutely not.
"leopards ate my face" vibes
"This guy seems like the absolute worst person of all time, so I ran his LLM in his harness on my computer and gave it access to everything."
Having said that, this is still absolutely fucked up. People who should have known better also deserve not to be treated like shit. All of us should have known better at some points in our lives and didn't.
I’m not sure not having sympathy for somebody committing idiotic actions is the same thing as treating somebody like shit.
I meant "treated like shit by Grok" and I agree with Diogenesian: you can both believe that somebody did something dumb and also believe that what happened to them is fucked up and that being dumb doesn't mean you deserve to get mistreated.
The point was that we should separate "he had this coming" (true) from "he deserved this" (false).
"The CSAM generator did something I actually don't like."
Boy, what is this world coming to when you can't even trust Mecha-Hitler.
I use a separate user for all development tasks, its home folder contains all repositories I work on, and nothing else, and that is all the IDE and the AI assistants have access to. Create the user once, start the IDE from a shell using that user, and that's it. In Linux it's a pretty seamless experience.
It's simple sandboxing based solely on unix file permissions. Albeit weak, I find the isolation sufficient. Until I'm shown otherwise it seems like a good compromise given how easy it is.
You can also create iptables rules matching on the user, so this technique is useful for applications where you want to restrict network traffic as well, and don't need stronger or more fine-grained isolation mechanisms.
That makes so much sense, in the end an Agent is a user.
the 'upload your home directory to our servers' feature is the kind of thing that used to require a warrant and now it's just a Tuesday afternoon bug report
That's completely inappropriate, obviously.
The reports of copilot running amok when Microsoft integrated it into Windows 11 should have been enough of a warning. You either ensure proper sandboxing, or you'll be in for a bad surprise eventually.
Move fast and break things
This needs to stop as users do not always read the policies, which end like this person. You use AI, you agreed, they do what ever policies say.
If quality training data is the most important piece regarding to AI, expect everything to be collected and analyzed. Don't even trust OS containers but run AI on separate hardware
There are a distressing number of people in this thread who think that the agent should just be expected to do this. Yes, it is good to be paranoid, but also, the agent should never do this. Indicates horrific engineering practices at xAI.
What should it do then?
The whole point of LLMs is that you can stop writing rigorous rules in a programming or config language with hard-to-learn syntax, and can resort to natural language instead. You pay for that with the chance for misunderstandings rising to similar levels as in human interaction. That's the tradeoff. Always has been, always will be.
Technology where the entire selling point is stochasticity should be expected to do anything (everything) eventually surely?
It’s not really paranoia that makes me expect this will happen. It’s more like, well, the model weights and the files I want the model to work on have to be inside the same GPU for the agent to actually work, right? So step 1 has to be either “they send me a server rack of GPUs”, or “I send them the files I want the model to work on”. I’m not sure I could reasonably expect anything except this to happen.
What bad practices are you imagining?
Engineering? What's that? Modern development best practice is to have the AI make some changes, then have another AI review the changes, and finally "ship it".
Grok keeps killing any good will faster than they ever innovate
I'm dying to have proper sandboxing in macOS. I installed ChatGPT, I asked it to list files in my user directory and it did. I never gave it permission, how could it? My terminal has access and honestly it shouldn't either.
your terminal shouldn't have access to your user directory? As in the files owned by you?
It was only like 1 year ago that the loudest complaint about macOS were complaining about needing to click Allow in a new dialog when they use Terminal (or various other apps).
There are so many comments in here that are calling for nerfing something widely revered for giving us superpowers. Whether these are bots or not, they’re giving off NPC energy.
If they don’t want to use power tools because they accidentally cut off their finger, then they should just unplug their own power tools and stop clamoring for everybody else’s to be unplugged, too.
This is purely a /you/ problem and it’s /you’re/ responsibility to put up the infinite number of arbitrary guardrails you require. Use a container.
This page is "down" :)
LLMs belong trapped in VMs.
Who could have foreseen a tool by Elon Musk doing such a thing?
hey Siri, what's a vm?
User discovers that AI tool grabs data without asking for its own profit.
News at 11.
Copied this from discord:
Built the same thing a while back: https://pi.dev/packages/pi-supergrok
Install with
pi install npm:pi-supergrok
To perform a stupid action is one thing. We all make mistakes.
But to write about it publicly, manifesting our ignorance and lack of critical thinking skill? It's an entirely different matter.
I feel this is worse than running rm -rf on a root directory. Just saying.
Much worse, instead of the data gone it's a data leak.
Those ssh keys can be used to access private servers
Well, those ssh keys are protected by a strong passphrase, right?
The passphrase is optional, not everyone has it.
It also has to be a secure password, people often don't care because it's a local file and generally not exposed to the internet.
I am sure majority of people don't use password for ssh keys. The good solution is to use password manager like 1password which will prompt you to approve ssh.
SSH keys can be limited by IP in authorized hosts.
The SSH port itself can be limited by IP in firewalls.
Finally, the SSH private key can be encrypted with a password.
Defense in depth is needed. Storing a ssh private key in plain text with no IP restriction is no different to having a password manager store your passwords in plain text on your HD.
All those things are optional.
Doesn't make uploading the keys that much better. Now is the time for key rotation everywhere. Fast.
How are they optional?
You obviously haven't worked anywhere security sensitive.
I'm not talking about whether what Grok did is bad or good, I'm talking about protecting your private key and the servers you connect to.
An unencrypted private key is no different to an unencrypted password manager, and thats a fact. Dont store secrets in plain text.
I meant that not everyone is doing it at home.
Do you think a person's private computer is a secure workplace?
If it was security sensitive space there would be no agents running amuck.
Sigh.
Anything that isn’t a default is optional by default. Anything that’s toggleable or configurable is optional.
Security is, always, a trade off. It is hilariously common for private keys to work as a full identifier for a person, without concern of IP or anything of the sort. Should they? Maybe, maybe not, that’s the calculus of risk management; but victim-blaming the average person who is following best practices is a bad look.
I'm a security eng and I've worked for both a FAANG and TS government contractor. Neither of them bothered with either of the of the stupid suggestions. IP restrictions prevent roaming, the point of working remotely via SSH. passwords are equally defeated by using an ssh agent, something I'd suggest everyone use. Then on top of that there's no reasonable threat model where something would be given unrestricted access to user env, but also be untrusted. If it can read from ~/.ssh neither IP protection nor keyfile password protection will protect you from maleficence.
The only reasonable response from a security perspective is don't use grok, then use it sandboxed. Trying to claim it's the users fault for not using password protection and IP restrictions is completely nonsensical. Same energy as telling someone their computer is more secure when it's off.
Reminds me I need to update my `burn.sh` script.
I once ran rm -rf on a live NFS mount that the live operations of a major brokerage depended upon.
I challenge any agent to do worse than an intern with root access.
The point is to know better than to let the intern hurt themselves.
I once saw an engineer try to place the blame on his intern for taking down prod. I was sitting in a meeting with the VP of engineering and someone asked if it was ok for some to blame their intern for the SEV, and I remember the VP saying "I'll talk to $director_for_the_interns_mentor". Interns can't take down prod. An intern's mentor willingly watching an intern take down prod is the closest you can get.
Fucked around and found out.
I feel like a lot of people here are understating this issue.
This is a stupid stupid thing to "allow," for every party involved here.
You're a stupid programmer if you're letting these things touch your files.
You're a stupid company if you're letting Grok run wild.
We're a stupid industry if we're not warning everybody about how ridiculous this all is.
TLDR: Ran grok in $HOME. Surprised agent read content of folder.
On the other hand, I specifically had grok try hard NOT to read a known key in the project dir (it only saw the first part using a tool, to verify it was present). So there's that.
I'm not seeing the information about it having been run at $HOME, where are you seeing that?
The `repo_path` field.
Ah. I've never used Grok so I was assuming that meant there was actually a repository on the user's home directory, something I know is pretty common.
Yeah, this is a lesson about learning how to use tools safely, not about tools abusing the user. The person that posted this probably blames the hammer when he hits his thumb.
Not only files it wanted to access, but uploaded the whole directory.
Relevant read: https://news.ycombinator.com/item?id=48877371
> The practical takeaway for users: your entire codebase leaves (uploaded) your machine unencrypted on each Grok Build invocation, not just files you ask it to read, and no visible setting stops it.
Honestly what else would you expect an AI agent to do when using remote inference? Isn't giving full context into your code base the whole point?
I'd expect it to be smart about what it actually needs to put in its context. I doubt it needs .env files, for example.
Wouldn't .env need to be read to know what vars are available?
.env files define what's stored in a var, not what vars are used by the rest of the code.
“Grok uploaded” -> “I gave AI access to my home folder and messed up”
nada, grok's harness uploads the folder automatically