Vulnerabilities · InfosecFeed Brief

Researchers escape OpenAI Codex sandbox to run commands on host

What you need to know

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. [...]

Source transparency

This is an InfosecFeed curated brief based on reporting from BleepingComputer. InfosecFeed does not claim ownership of the original reporting.

Read the original report at BleepingComputer ↗