Researchers escape OpenAI Codex sandbox to run commands on host

BleepingComputer1 mo ago

Illustration · AI security

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. [...]

Continue reading at BleepingComputer →

Researchers escape OpenAI Codex sandbox to run commands on host

More on this

Google Says Gmail and Photos Data Shared With AI Search Could Be Used for Targeted Ads

Researchers Push Over 2 Million Updates to Remotely Disable Popcorn Time Updater That Could Fuel a Botnet

BlackX UEFI Bootkit Bypasses Secure Boot on Patched Windows Systems Missing Revocations

UK proposes 14-year prison terms for undersea cable sabotage

Torvalds: AI is fine for competent devs, but spare us the 'drive-by' patches

Arista patches new VeloCloud Orchestrator zero-day exploited in attacks