I'm confused: 1. If I run this on Mac, then inside the sandbox / microVM, am I still running MacOS or some Linux distribution? 2. If the only thing that's mounted from the host is the $PWD, how does it guarantee that it has all the system libraries that I have installed on my host system? e.g. my `/opt/homebrew` libraries or `sudo apt install libfoo-dev` headers
Docker Sandboxes – Disposable, isolated sandboxes for AI agents
201–210 of 440 posts
Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#202Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#203Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#204Earlier quoted context omitted.
It’s injected into an outbound api call, not into an env var the agent can read.
what's to stop an agent creating an outbound call with the var to a malicious endpoint? (unless you whitelist what it has access to)
Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#205The login is annoying but, lacking an open source alternative, this has been my daily driver for a while now because it works great out of the box with two key features: outbound firewall and secret injection with placeholders. I run it with superset and then each git worktree is mounted in a sandbox that is configured for each repo i work in. Closest open source I have seen is https://earendil-works.github.io/gondol…
Internally uses a single VM + Incus containers, supports docker/Kubernetes in each sandbox, has integrated worktree management.
Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#206Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#207Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#208Earlier quoted context omitted.
It’s injected into an outbound api call, not into an env var the agent can read.
what's to stop an agent creating an outbound call with the var to a malicious endpoint? (unless you whitelist what it has access to)
Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#209Earlier quoted context omitted.
You want to prevent the agent/others from reaching your home directory and other things. As long as you don't mount/sync directories/files from/to the container, so no mounting like "-v $(pwd):/app", but instead copy in, then when done, copy out. And of course, instead of doing the "copy in > copy out" process manually, get your local agent to write a bash script that does that for you, given what directory you're in…
What is the advantage of copying rather than a bind-mount?
Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents
#210The login is annoying but, lacking an open source alternative, this has been my daily driver for a while now because it works great out of the box with two key features: outbound firewall and secret injection with placeholders. I run it with superset and then each git worktree is mounted in a sandbox that is configured for each repo i work in. Closest open source I have seen is https://earendil-works.github.io/gondol…