Hacker News Reader

Comment by thwarted | Hacker News Reader

Generally a good idea, but I'm not sure why you should even want to fork a git repo when a local clone should be sufficient. But this is probably a terminology mixup from the way github presents forks and clones.

View on HN

I believe the author's idea is to do dev work from a Github account that only has access to the fork, but not to the main repo. Then, as a contributor, you'd open PRs from your fork to the main repo. I think this would only work if your Github account doesn't have write access to the main repo, though. I know you can use 'deployment keys' to give read-access to a single repo using an SSH key, but not sure if you can otherwise restrict access to a single repo with write access. Essentially, though, you'd want to find a way to give the remote host the most limited possible privileges to your Github account.

Oh, a separate GitHub account that has its own forks of the repos the agent is working on. Yeah, that's probably the most secure, isolated, and safest. The merge to the canonical repo then needs to go through a human, or at least separately controlled, process via a GitHub pull request.

You could also just set the development machine up as a remote on the repo on your local host and then pull, diff, and merge locally. Then the llm agent doesn’t have access to any github account at all.

I use an overlay copy of my workdir, then the sandboxed LLM doesn't get any of my secrets, can do its own commits, and I pull the ones back that I want.

On a GitHub project, agents must just be considered untrusted external contributors.

Maybe this is doable with scoped API keys instead of SSH keys?

They mention that as a mechanism for protecting the SSH keys for the repo.

Essentially using a repo that doesn’t matter with the coding agent and then creating a cross-repo PR to the real repo.

Reply on news.ycombinator.com