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.

Two OpenAI Codex sandbox flaws, Overpatch and Heapjack, could let malicious repositories execute commands on developer systems.

Codex’s network proxy was resolving a hostname before it checked whether that host was allowed, so the name went out to ...

Note: before troubleshooting, js_repl was false; changing it to true and retrying in the current thread did not change the failure. A full Desktop restart may still be required for that setting to ...

Security researchers broke out of the sandboxes in four widely used AI coding agents, including Cursor, OpenAI's Codex, Google's Gemini CLI and Antigravity, without attacking the sandbox head-on. The ...

Cosa è successo Oren Yomtov of Accomplish AI conducted authorized security research on the OpenAI Codex sandbox and identified two conceptual flaws, which the researchers named Heapjack and Overpatch.