Menu

1 / 5

I Sandboxed My AI Coding Agent with Bubblewrap. It Still Read My Secrets

DEV Community·Krishna Tej Chalamalasetty·17 days ago
#DNAA0v8c
#dev#sandbox#root#namespace#agent
Reading 0:00
15s threshold

Three Decisions, Three Places

Same agent. Same sandbox. Different folder. Different blast radius.

Coding agents run real commands on your machine. A README, an issue or a dependency can steer what they run. I kept seeing posts saying agents behave differently depending on where you launch them: / , ~ or ~/dev . I wanted to know why at the kernel level, not just that they do.

So I wrapped a minimal coding agent in a sandbox I built myself, traced every process it started, and asked one question about every result: which flag decided this, and where in the kernel does that decision happen?

The short version: a bubblewrap sandbox answers three separate questions in three separate places.

Can it write? Decided by the mount the path lives on.

Can it read? Decided by the file's owner and mode bits , the same as outside the sandbox.

Can it talk? Decided by the network namespace the process is in.

My policy controlled the first one well.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.