Tag: Codex

  • Researchers Escape OpenAI Codex Sandbox to Run Host Commands

    Researchers Escape OpenAI Codex Sandbox to Run Host Commands

    Security researchers discovered two ways to escape the OpenAI Codex sandbox and reach resources on the host computer. OpenAI reportedly fixed both vulnerabilities within eight days, but one flaw enabled command execution from the strictest sandbox mode. Researchers Discover Two Codex Flaws Oren Yomtov of Accomplish AI and fellow researchers reported both vulnerabilities to OpenAI…

  • Codex agent failure disrupts Linux cyberattack analysis

    Codex agent failure disrupts Linux cyberattack analysis

    A Linux cyberattack investigation took an unexpected turn when an AI tool complicated the process instead of helping it. The Codex agent failure added confusion at a critical moment. As a result, analysts struggled to separate real threats from AI-generated activity. Codex Agent Failure Disrupts Investigation The Codex agent failure occurred during an attempt to…