[e1g]

Here's my ruleset https://gist.github.com/eugene1g/ad3ff9783396e2cf35354689cc6...

My goal is to prevent Claude from blowing up my computer by erasing things it shouldn't touch. So the philosophy of my sanboxing is "You get write access to $allowlist, and read access to everything except for $blocklist".

I'm not concerned about data exfiltration, as implementing it well in a dev tool is too difficult, so my rules are limited to blocking highly sensitive folders by name.

[icedchai]

That's neat. I'm going to base my ruleset off of yours. I've been messing around with claude more and more lately and I need to do something.

[AdieuToLogic]

> Here's my ruleset ...

Thank you for sharing a non-trivial working example of a sandbox-exec configuration. Having an exemplar such as what you have kindly shared is hugely beneficial for those of us looking to see what can be done with a tool such as this.

[e1g]

Thank you - you inspired me to open-source this work properly -> https://eugene1g.github.io/agent-safehouse/