I mean, it depends on what you're doing but I force claude to always commit code every time it finishes a todo. It never seems to stop doing that, so I run it in dangerous mode on Zed. I get to review the code after the fact anyway.
The danger there is not that it commit bad things, but that as part of working the task it gets tricked into sending your env/secrets/credentials to prompt injectors. That would not show up in your commit diff.
Edit: At the very least, I would not allow it to do indiscriminate web searching.
The risk isn’t that it makes weird commits; it’s that it may decide to clean up stuff and delete more than desired.
- https://github.com/anthropics/claude-code/issues/4331
- https://github.com/anthropics/claude-code/issues/7787
- https://news.ycombinator.com/item?id=46268222