Live data from Hacker News

Codex just found a "workaround" of not having sudo on my PC

twitter.com

41–50 of 330 posts

Re: Codex just found a "workaround" of not having sudo on my PC

#41

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.

That’s the workflow feature I badly want: for it to create a side list of things like that. Currently it either accumulates slop or goes on side quests far too easily. This might be as easy as a directive to populate a .md file.

> This might be as easy as a directive to populate a .md file.

It probably is. But do you really think anyone is gonna bother with the multiple daily (or hourly for green field projects) `+8,234/-3,734` PRs everyone is submitting?

The joke I was referring to is the common

     // ksmith (3/23/1997): This is a temporary hack for now. Find a better way to do this asap.

Re: Codex just found a "workaround" of not having sudo on my PC

#42
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.

Re: Codex just found a "workaround" of not having sudo on my PC

#43
post #40

Earlier quoted context omitted.

The "attack vector" people try to protect themselves is "agent edited wrong file", not "LLM blew 0day on escaping sandboxing", containers are more than enough for what stupid stuff agents sometimes try, no need to go for a full-blown VM. Even UNIX permissions would be enough, but I think that's lost knowledge at this point.

Using the least amount of security features is a huge amateur mistake. Best practice is to use 2 redundant layers of security, such that if one fails, there is still another one. Using just the minimum amount of security technically possible is almost by definition hubris. An example would be that you never point a gun at someone you don't want to shoot, regardless if there's bullets in the gun. If someone tells you,…

This is true but it's not really a security scenario. The LLM isn't an attacker it's just an unreliable tool.

Re: Codex just found a "workaround" of not having sudo on my PC

#45
post #7

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.

I recently switched over to podman and it's been great!

Re: Codex just found a "workaround" of not having sudo on my PC

#46

Run coding agents in a docker container with limited permissions. FWIW, I run it with --cap-drop=ALL --pids-limit=4096 --runtime=runsc

Or put it in a microvm using eg smolmachines.

I've never used smolmachines but I'm curious; why this over a container?

Re: Codex just found a "workaround" of not having sudo on my PC

#47
post #40

Earlier quoted context omitted.

The "attack vector" people try to protect themselves is "agent edited wrong file", not "LLM blew 0day on escaping sandboxing", containers are more than enough for what stupid stuff agents sometimes try, no need to go for a full-blown VM. Even UNIX permissions would be enough, but I think that's lost knowledge at this point.

Using the least amount of security features is a huge amateur mistake. Best practice is to use 2 redundant layers of security, such that if one fails, there is still another one. Using just the minimum amount of security technically possible is almost by definition hubris. An example would be that you never point a gun at someone you don't want to shoot, regardless if there's bullets in the gun. If someone tells you,…

> Using the least amount of security features is a huge amateur mistake.

Not understand your threat I'd say would be a even bigger amateur mistake, you're not trying to protect yourself against some forever 3rd party attacker here, you're trying to prevent a agent rewriting the wrong file on your disk, that's basically it.

Give it the least amount of permissions, don't bi-directionally sync stuff, pass things in, then take them out again, literally the agent couldn't and wouldn't try to break through 2 layers of security in order to get your banking details or whatever.

Re: Codex just found a "workaround" of not having sudo on my PC

#48
post #40

Earlier quoted context omitted.

Using the least amount of security features is a huge amateur mistake. Best practice is to use 2 redundant layers of security, such that if one fails, there is still another one. Using just the minimum amount of security technically possible is almost by definition hubris. An example would be that you never point a gun at someone you don't want to shoot, regardless if there's bullets in the gun. If someone tells you,…

This is true but it's not really a security scenario. The LLM isn't an attacker it's just an unreliable tool.

all unreliable tools are attackers. Even if you're using well-aligned LLMs like Opus, you should assume that any input you give it -- including all dependencies from npm, etc. -- are at risk of compromise, which could result in attempted exfiltration of data or system takeover. You can be absolutely sure that there are thousands of well-motivated hacker groups, both national and private, looking for ways in.

Re: Codex just found a "workaround" of not having sudo on my PC

#49
post #7

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.

I recently switched over to podman and it's been great!

Podman on Windows - never been able to fully get rid of it and it throws errors on boot after uninstall. Was a fan, am now not.

Re: Codex just found a "workaround" of not having sudo on my PC

#50
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.

Post reply on HN