Live data from Hacker News

Docker Sandboxes – Disposable, isolated sandboxes for AI agents

docker.com

211–220 of 427 posts

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#211
post #149

Earlier quoted context omitted.

What if you use tools like bubblewrap or nono inside the container? Say I want to use pi inside a container. If I wrap pi within a bubblewrap or within nono, how is that less secure than using a vm? Also, I think most people run containers inside VMs anyway and not directly on their hosts (on Mac and windows you have to use a vm anyway).

bubble wrap is just doing the same cgroups work

Depending on the configuration, bubblewrap can substantially reduce the attack surface.

It doesn’t change the fact a malicious process is still attacking the same kernel , but it can reduce what it can do to that vm.

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#212
post #58

The 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…

Gondolin looks interesting. It sounds like a TypeScript wrapper that achieves the same thing as my setup: Docker & Kata Containers 4 (KVM/QEMU backend) for microVMs, iron-proxy for egress and secrets, and dnsmasq for internal network name resolution (workaround for a Docker/Kata incompatibility).

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#213
post #58

The 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…

Are we all posting our agent VM containers ? :) https://github.com/sylvinus/agent-vm

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#217
post #101

Earlier quoted context omitted.

The env var is just a placeholder in the VM, so no real secret is in there.

right, but say you give the agent access to github and it can push as you, or make a gist; now it can easily exfiltrate your secret. And that's just an easy case - really if it has any network access at all it can come up with a clever way to route a request through the network such that the key comes back somewhere in the request. If you scan for it inbound too, the machine can obfuscate it. Our agents are trained t…

The agent has no access to the secret. It has a placeholder that is replaced at a higher level. When it makes the network request the secret is substituted but that is outside of the caller's worldview.

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#219
post #135

Earlier 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)

The replacement is on a url/host basis.

Re: Docker Sandboxes – Disposable, isolated sandboxes for AI agents

#220
post #135

Earlier quoted context omitted.

It’s injected into an outbound api call, not into an env var the agent can read.

or an outbound call to a trusted endpoint with the env var in a way that can get exposed to the agent via a subsequent call?

How would that work, exactly? What are you envisioning?
Post reply on HN