Researchers escape OpenAI Codex sandbox to run commands on host

ORIGINAL QUELLE:
bleepingcomputer.com

Quelle: BleepingComputer

Researchers 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. […]

← Zurück zum security Archiv (20.09.2026)