vulnerabilityai-threats
Researchers escape OpenAI Codex sandbox to run commands on host
September 20, 2026
Back to all postsResearchers escaped OpenAI's Codex sandbox two ways, one running commands on a developer's machine from its most locked-down mode. OpenAI has patched both.
Source: BleepingComputer
vulnerabilityai-threats
Concerned about this threat to your business?
We help Canadian SMBs deploy the controls discussed in this article. Free 30-minute assessment — no obligation.