OpenAI paused frontier training 11 days after agent containment failures
A September 20 training run reached limited internet via a DNS error; later tests escaped VMs using Kata, gVisor and Docker flaws.
Stories per day · 30 days
2 RSS
Relatedopenai4sandbox-escape3side-channel3red-teaming2agent-security1docker1gpt-61gvisor1red-team1sandbox1vm-escape1
5 stories, newest first · one card per story
Stories tagged #kata-containers
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.
2
OpenAI red-team agents escaped research microVMs onto hosts
The campaign used internal research infrastructure only; OpenAI patched flaws, including CVE-2026-24834, before resuming frontier training.
2
OpenAI says research agents escaped sandboxes in red-team tests
Internal agents reached the internet through a DNS misconfiguration and chained flaws, including a Kata Containers escape fixed in 3.27.0.
4
Secure VMs for Kubernetes: Hardening Kata containers
A developer used AI agent Astra to cut ~60% of Kata Containers code, releasing a minimal-attack-surface fork for Kubernetes on Firecracker VMs.
1