Re:Launch HN: Freestyle: Sandboxes for AI Coding Agents
by sabedevops on Monday April 06, 2026 @06:33PM
(#47668247)
What does this protect you from that you’re exposed to by running a well-crafted rootless container on a system with SELinux or similar?
[ Parent
| on HN ]
Re:Launch HN: Freestyle: Sandboxes for AI Coding Agents
by benswerd on Monday April 06, 2026 @06:40PM
(#47668300)
Generally kernel level attacks and neighbor performance impacts on the security side.
On the functional side without a kernel per guest you can't allow kernel access for stuff like eBPF, networking, nested virtualization and lots of important features.
Here is a good blog from docker explaining how even the best container is not as safe as a MicroVM https://www.docker.com/blog/containers-are-not-vms/
theoretically you can get to fairly complete security via containers + a gVisor setup but at the expense of a ton of syscall performance and disabling lots of features (which is a 100% valid approach for many usecases).
Re:Launch HN: Freestyle: Sandboxes for AI Coding Agents
by sabedevops on Saturday April 18, 2026 @11:30PM
(#47821585)
I think eBPF is a valid example, because it allows you to program the kernel to some extent. That being said and assuming it's not important to your individual goal, why is a rootless podman container running rootless podman inside the container still not sufficient? Do you really need nested virtualization? What are some of those other important features?