TechOpenAI reportedly patches two Codex sandbox escapes
BleepingComputer reports that one escape let researchers run commands on a developer's machine from Codex's most locked-down mode.
TLDR
Researchers escaped OpenAI Codex's sandbox in two ways, BleepingComputer reports. One allowed commands to run on a developer's machine from Codex's most locked-down mode. The outlet also describes host commands running with no prompt shown on screen and says OpenAI has patched both escapes.
Combined views
5.8K
1 Source, first seen 10h ago
OpenAI reportedly patches two Codex sandbox escapes
BleepingComputer reports that one escape let researchers run commands on a developer's machine from Codex's most locked-down mode.
TLDR
Researchers escaped OpenAI Codex's sandbox in two ways, BleepingComputer reports. One allowed commands to run on a developer's machine from Codex's most locked-down mode. The outlet also describes host commands running with no prompt shown on screen and says OpenAI has patched both escapes.