OpenAI Codex Sandbox Flaws Let Malicious Repositories Execute Commands on Host Systems
Two OpenAI Codex sandbox flaws, Overpatch and Heapjack, let malicious repositories execute unsandboxed commands on developer hosts; both are patched.
2
1 stories, newest first · one card per story
Two OpenAI Codex sandbox flaws, Overpatch and Heapjack, let malicious repositories execute unsandboxed commands on developer hosts; both are patched.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views