OpenAI Red-Teamed Its Sandboxes and Found a CPU Side Channel
This story is from 2026-10-28. It is preserved in the archive; the latest stories are on the live feed.
Originally published at webofmike.com on 2026-10-28. The demo repo and every command in it were run before publishing. OpenAI spent hundreds of billions of tokens trying to break its own agent sandboxes, and its agents won often enough to patch a Kata Containers CVE, a gVisor bug, a Docker syscall…
Read the full story at DEV Community — AI ↗
Timeline · 1 report
- 2026-10-28 16:18 · DEV Community — AI
OpenAI Red-Teamed Its Sandboxes and Found a CPU Side Channel