News for hackers. Stuff that matters.
Re:Show HN: Nono – Kernel-enforced sandboxing for AI agents by sukinai on Sunday February 01, 2026 @04:58PM (#46849790)
This hits the real problem: once agents execute code, “please don’t read ~/.ssh” is not a security control. Kernel-enforced isolation + tight allowlists is. The secrets workflow (keychain/secret service → env → zeroize) is especially practical. Biggest thing I’d want as a user is very explicit docs on the remaining gaps (macOS read-permissive mode, procfs/env/subprocess behavior, and what Landlock can’t cover yet vs seccomp). If that’s clear, this could be a default wrapper for local agent runs.

There are no comments on this comment yet.