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.

"BragJack" has been released, a method for hijacking AI assistants running within browsers—such as Chrome, Edge, Perplexity Comet, Opera Neon, and Claude in Chrome—via malicious extensions. In OpenAI ...

AM JST today, includes four combined fixes for paths where credentials that should have been masked were appearing in logs ...

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. OpenAI admits it did not disclose an ...

Google has rolled out Chrome 154 to the Stable channel for Windows, Mac, and Linux, delivering fixes for 108 security vulnerabilities.

Google on Tuesday released updates to patch 230 security vulnerabilities, including one that has come under active exploitation in the wild. The medium-severity vulnerability, assigned the CVE ...

Google has rolled out Chrome 153 to the stable channel for Windows, Mac, and Linux, shipping as version 153.0.8010.36 on Linux and 153.0.8010.36/.37 on Windows and Mac.

Chrome users have another zero-day problem on their hands. Google has patched CVE-2026-87491, a vulnerability in the V8 JavaScript and WebAssembly engine that attackers are already exploiting in the ...

OpenAI is expanding Codex with reusable cloud development environments, a revamped CLI with voice controls, new code review ...

There are different definitions of Agent Sandboxes circulating, but the strictest defines it as an isolated runtime in which an agent's tool calls execute under constraints that the agent cannot ...