I trust sandbox-exec more, or Docker on Linux. Those come from the OS, well tested and known.
MITM proxy is nice idea to avoid leaking secrets. Isn’t it very brittle though? Anthropic changes some URL-s and it’ll break.
MITM proxy is nice idea to avoid leaking secrets. Isn’t it very brittle though? Anthropic changes some URL-s and it’ll break.
Re the URLs, I agree, that's why I added wildcard support, e.g. `*.openai.com` for secret injection as well as network call filtering.
That being said, the default behaviour is no network, so nothing will be routed if it's not allowed regardless of whether the sandboxed process respects env vars or not.
BUT, the default behaviour (no net) is fully enforced at the kernel level. Domain filtering relies on the program respecting proxy env vars.
(allow network-outbound
(remote tcp "127.0.0.1:8080"))