Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

A way to exclude sensitive files issue still open for OpenAI Codex

github.com

Post reply on HN
Print view View original

101–110 of 157 posts

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#101

Post by SubiculumCode »

kstenerud wrote: post #48
TheDong wrote: post #4

You can do this now: change the file permissions such that the user you run codex as can't read them, or run codex in a container without those files mounted. If you don't do that, the agent will be able to incidentally upload them. What if the model runs "rg foo", and one of those files contains the string "foo"? It uploads the tool output, which includes the file contents. And so, the only solution is to make it so…

If you're not sandboxing your agent, everything on your computer is waiting to be exposed. Assuming that file permissions will save you is naively dangerous.

What is your sandbox approach? Any good guides? Something about asking a LLM for advice on how to sandbox LLMs.....

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#102

Post by kstenerud »

SubiculumCode wrote: post #101
kstenerud wrote: post #48

Earlier quoted context omitted.

If you're not sandboxing your agent, everything on your computer is waiting to be exposed. Assuming that file permissions will save you is naively dangerous.

What is your sandbox approach? Any good guides? Something about asking a LLM for advice on how to sandbox LLMs.....

I use this: https://github.com/kstenerud/yoloai

    yoloai new mysandbox .   # Create a sandbox
    yoloai attach mysandbox  # Attach the sandbox to the current terminal
    ... (^b^d to disconnect) # It's using tmux to keep the agent alive
    yoloai diff mysandbox    # See what the agent did
    yoloai apply mysandbox   # apply its changes to your workdir
    yoloai destroy sandbox
You can also make it run a prompt and block until it's done:

    yoloai run mysandbox . -p "read issue https://github.com/kstenerud/yoloai/issues/190 and fix it"
    yoloai diff mysandbox
    yoloai apply mysandbox
    yoloai destroy sandbox

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#103

Post by kstenerud »

efxhoy wrote: post #99
kstenerud wrote: post #48

Earlier quoted context omitted.

If you're not sandboxing your agent, everything on your computer is waiting to be exposed. Assuming that file permissions will save you is naively dangerous.

How could an agent bypass file permissions?

By exploiting a root escalation.

Or just finding a file/dir you forgot to set a tight enough mode on (happens a lot in systems where the default is insecure).

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#104

Post by kgwgk »

cataphract wrote: post #95
atomicnumber3 wrote: post #72

Earlier quoted context omitted.

We managed to generate probably-correct code, which can then be probably-corrected recursively to get to something that runs (usually). This made everyone scream and lose their minds saying that code is finished, people think they don't need a technical cofounder anymore, think they don't need engineers anymore, etc. Then they're, at varying speeds, finding out they're wrong. It seems oddly circular to me that the _e…

That is not a fault that's specific to engineers. Lots of smart lawyers think they can learn basically anything over a weekend of hard study. It's probably a blind spot of intelligent people.

https://xkcd.com/793/

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#105

Post by laweijfmvo »

embedding-shape wrote: post #44
cowsandmilk wrote: post #15

Earlier quoted context omitted.

100% this. The idea that Codex should enforce this is putting the security boundary at the wrong layer. If you don’t want codes to access something, make it so it doesn’t have access.

The Codex bug tracker is a great insight into how wide the knowledge gap seem to be between users. The issue where people ask them to add back /undo or whatever it is instead of just learning to use git, probably reached 100 comments at least by now. People seemingly don't really understand the computers they use on a daily basis, and refuse to learn too.

huh, but what if the AI trashes my git repo? maybe it just deletes the .git folder entirely. a deterministic undo wouldn’t be the silliest feature, for the current definition of “AI”.

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#106

Post by throwatdem12311 »

cowsandmilk wrote: post #15
TheDong wrote: post #4

You can do this now: change the file permissions such that the user you run codex as can't read them, or run codex in a container without those files mounted. If you don't do that, the agent will be able to incidentally upload them. What if the model runs "rg foo", and one of those files contains the string "foo"? It uploads the tool output, which includes the file contents. And so, the only solution is to make it so…

100% this. The idea that Codex should enforce this is putting the security boundary at the wrong layer. If you don’t want codes to access something, make it so it doesn’t have access.

You expect Joe Blow vibe coder running Codex on his Dell to understand this?

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#107

Post by mirashii »

laweijfmvo wrote: post #105
embedding-shape wrote: post #44

Earlier quoted context omitted.

The Codex bug tracker is a great insight into how wide the knowledge gap seem to be between users. The issue where people ask them to add back /undo or whatever it is instead of just learning to use git, probably reached 100 comments at least by now. People seemingly don't really understand the computers they use on a daily basis, and refuse to learn too.

huh, but what if the AI trashes my git repo? maybe it just deletes the .git folder entirely. a deterministic undo wouldn’t be the silliest feature, for the current definition of “AI”.

The default sandboxing for Codex does not allow the agent to access .git

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#108

Post by throwatdem12311 »

MattDamonSpace wrote: post #35
cowsandmilk wrote: post #15

Earlier quoted context omitted.

100% this. The idea that Codex should enforce this is putting the security boundary at the wrong layer. If you don’t want codes to access something, make it so it doesn’t have access.

Not sure I agree? It’s not like gitignore should be independent from git

Will git drop your production database because it feels like it when the stars align?

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#109

Post by matheusmoreira »

throwatdem12311 wrote: post #106
cowsandmilk wrote: post #15

Earlier quoted context omitted.

100% this. The idea that Codex should enforce this is putting the security boundary at the wrong layer. If you don’t want codes to access something, make it so it doesn’t have access.

You expect Joe Blow vibe coder running Codex on his Dell to understand this?

Yes.

Re: A way to exclude sensitive files issue still open for OpenAI Codex

#110

Post by throwatdem12311 »

matheusmoreira wrote: post #109
throwatdem12311 wrote: post #106

Earlier quoted context omitted.

You expect Joe Blow vibe coder running Codex on his Dell to understand this?

Yes.

lol I don’t you realize how tech illiterate most normies are
Post reply on HN