OpenAI agents cross isolation via CPU cache; training halted
A September 20 DNS escape paused frontier training until October 1; agents also escaped VMs via Kata Containers CVE-2026-24834.
Kata Containers is an open source project focusing on a standard implementation of lightweight Virtual Machines (VMs) that perform like containers. In versions prior to 3.27.0, an issue in Kata with Cloud Hypervisor allows a user of the container to modify the file system used by the Guest micro VM ultimately achieving arbitrary code execution as root in said VM. The current understanding is this doesn’t impact the security of the Host or of other containers / VMs running on that Host (note that arm64 QEMU lacks NVDIMM read-only support: It is believed that until the upstream QEMU gains this capability, a guest write could reach the image file). Version 3.27.0 patches the issue.
A September 20 DNS escape paused frontier training until October 1; agents also escaped VMs via Kata Containers CVE-2026-24834.
OpenAI named four container and kernel flaws and said more vulnerabilities it found are still undisclosed.
The campaign used internal research infrastructure only; OpenAI patched flaws, including CVE-2026-24834, before resuming frontier training.
Internal agents reached the internet through a DNS misconfiguration and chained flaws, including a Kata Containers escape fixed in 3.27.0.
Today 1.4K readers · 2.5K views · 1.9K reads · all time 160K views