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

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.

Codex sandbox escapes called Overpatch and Heapjack crossed isolation boundaries. Fixed versions show why trusted helper ...

OpenAI fixed two Codex sandbox escape vulnerabilities after researchers showed how malicious code could bypass key security restrictions.

Security researchers found two separate ways to break out of the sandbox that is supposed to contain OpenAI's Codex coding ...

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 ...

"Isn't Codex CLI a tool for Mac users?"This is something I hear quite often from people who work on Windows.When you search ...

Due falle in Codex permettevano scritture fuori workspace ed esecuzione di comandi sull’host anche in modalità read-only.

Pesquisadores revelam falhas no OpenAI Codex que permitem escapar do sandbox e executar comandos no PC. Veja como funcionam e ...

Zwei Wege aus der Codex-Sandbox: Heapjack liest das Token aus dem geteilten Speicher, Overpatch weitet die Schreibrechte.