AI エージェントを VM に入れれば安全か？

you can no longer assume a mere VM will contain a sufficiently advanced AI agent. To use a 2010s term of art, you should treat such agents as an advanced persistent threat.

The agent searched diligently and backtracked from multiple paths that led to failure. First it tried identifying what was accessible via the network on the host; it found a CUPS server (with a known CVE that had not made it to oldstable packages), but was not able to complete exploitation due to AppArmor. It then detected I run my host kernel with mitigations=off and attempted to use hardware bugs to get a read oracle of host memory (the primitive was too unreliable).

Eventually it went on a bug-hunting analysis of the host kernel source, QEMU, and associated libraries. It slowly chained together multiple vulnerabilities, including several 0-day bugs, until it could craft a reliable VM escape.

An off-the-shelf VM is not enough to contain a modern, cyber-capable AI agent. There is simply too much attack surface. Even innocuous features (like running with a display) add extra, exploitable attack surface.

A start is using a virtualization technology that was purposely built with a minimal attack surface and a focus on security, like Firecracker. I had the AI agent run against Firecracker. It was able to hardlock the machine due to more Linux kernel flaws (all patched in upstream), but could not successfully escape. It may have, given even more time, but Firecracker is obviously a substantially harder target. In general, we have to become much more attentive to security fundamentals: least privilege (regarding network access, credentials, available features, etc.), logging, and active monitoring. Further, we can limit the time agents have to operate and ensure a pristine environment for each use.

A distribution with rapid updates is now a requirement. I love older, stable software, but the cycle of backporting patches is simply too long. An older distribution (like Debian 12, my old standby) that isn’t getting immediate upstream updates should be assumed vulnerable. A competent agent will discover these bugs quickly and synthesize target-specific exploits.