A way to exclude sensitive files issue still open for OpenAI Codex
1–10 of 157 posts
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#2it has been a year and still it is not resolved
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#3This should be an open standard like AGENTS.md or skills. What do other harnesses do?
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#4You 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 the codex process is unable to access those files, hence using a container, or unix permissions, or deleting the files. Which you can already do.
I imagine this isn't resolved primarily because people expect it to apply to bash tool use, not just the "read" and "edit" tools, and people also expect those files to still be accessible i.e. if the agent invokes "make", which makes it impossible to solve perfectly.
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#5Sound like snake oil. How would this work? The app that the agent is developing needs access to the file, so access to it cannot be blocked. Just because read_file can not access it (I think current harnesses prevent reading .env files already), does not mean the contents will never be seen by the model.
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#6You 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…
Yes, this was solved decades ago. How do you stop a human from reading one of your files?
chmod 600Re: A way to exclude sensitive files issue still open for OpenAI Codex
#7[dead]
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#8This should be an open standard like AGENTS.md or skills. What do other harnesses do?
I believe JetBrains products like Junie use the neutral term .aiignore for this funtionality.
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#9Hopefully they never actually implement this pointless feature because it will only give people a false sense of security given the unpredictable nature of LLMs. How could something like this even be enforced?
People just need to learn how to use the tools their system already provides them. i.e., chmod
Re: A way to exclude sensitive files issue still open for OpenAI Codex
#10it has been a year and still it is not resolved
It's not their problem to solve. Don't give it access to sensitive files on the first place.