Celesto has an unified interface for sandboxes based on QEMU, Firecracker and Libkrun.
Ask HN: Secure wrapper for coding agents?
21–26 of 26 posts
Re: Ask HN: Secure wrapper for coding agents?
#22If you are running MacOS, I would recommend Agent Safehouse. Well maintained and is built on existing sandbox-exec so you are not locked in and can always build your own rules independent of the CLI tool. https://github.com/eugene1g/agent-safehouse/ https://agent-safehouse.dev/ Originally posted on HN https://news.ycombinator.com/item?id=47301085
Seconding this. I've been running Safehouse for months and love that it can wrap any process (it's just a wrapper around the native macOS sandbox API, after all). The only thing I miss is the ability to limit network access, which isn't supported by the API.
Safehouse author here - glad you found it helpful. It didn't even occur to me to add --offline mode because my mental model is anchored in agents which often require network access. Until we add this, the easiest option is to create a custom policy and then reference it with Safehouse (I usually setup shell aliases/funciton for this)
;; in ~/.config/agent-safehouse/no-network.sb
(deny network*)
safehouse --append-profile="$HOME/.config/agent-safehouse/no-network.sb" -- Re: Ask HN: Secure wrapper for coding agents?
#23Earlier quoted context omitted.
Seconding this. I've been running Safehouse for months and love that it can wrap any process (it's just a wrapper around the native macOS sandbox API, after all). The only thing I miss is the ability to limit network access, which isn't supported by the API.
Safehouse author here - glad you found it helpful. It didn't even occur to me to add --offline mode because my mental model is anchored in agents which often require network access. Until we add this, the easiest option is to create a custom policy and then reference it with Safehouse (I usually setup shell aliases/funciton for this) ;; in ~/.config/agent-safehouse/no-network.sb (deny network*) safehouse --append-pro…
Hello! I was definitely not looking to block all network access. I would want to maintain a whitelist of hosts and IPs. I don't know if that's possible?
Re: Ask HN: Secure wrapper for coding agents?
#24Earlier quoted context omitted.
Safehouse author here - glad you found it helpful. It didn't even occur to me to add --offline mode because my mental model is anchored in agents which often require network access. Until we add this, the easiest option is to create a custom policy and then reference it with Safehouse (I usually setup shell aliases/funciton for this) ;; in ~/.config/agent-safehouse/no-network.sb (deny network*) safehouse --append-pro…
Hello! I was definitely not looking to block all network access. I would want to maintain a whitelist of hosts and IPs. I don't know if that's possible?
Unfortunately, no, MacOS sandboxing does not allow that type of blocking. Only broad categories like "local" vs "remote", but no selective targeting based on domain names or IPs.
Re: Ask HN: Secure wrapper for coding agents?
#25Beside from particular project, I would like to talk about my rule of thumb in agent usage, which is to separate “smart” from “authorized.”
That is, to build a state wrapper and separate agent from making runtime decision, a dangerous design is letting the same agent both decide and record the state of the system. If it hallucinates, you can hardly find the error.
Re: Ask HN: Secure wrapper for coding agents?
#26[flagged]