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.
Researchers escape OpenAI Codex sandbox to run commands on host
About this summary. This is a short, independently written summary of an article first published by BleepingComputer. Cyber Security News did not report or verify the underlying story. Read the original: https://www.bleepingcomputer.com/news/security/researchers-escape-openai-codex-sandbox-to-run-commands-on-host/
Source attribution: headline and facts are from BleepingComputer (bleepingcomputer.com). Summary method: excerpt of the source description. See our source attribution policy.
Related coverage
The AI plot to scan and destroy books (Lock and Code S07E19)
This week on the Lock and Code podcast… If you want AI to tell you a story, it will. If you want that story to sound like one of your favorite authors, it can. And if…
Dems seek top-to-bottom assessment of CISA workforce
A group of leading House Democrats introduced legislation Monday requiring the Cybersecurity and Infrastructure Security Agency to conduct an assessment of its workforce…
The fake sites using a cheap toolkit to sell $2,000 AI subscriptions
We found more than 100 subscription websites linked through the same toolkit and closely related developer details. Some impersonate existing products, including GPT-6…
From Love Letters to AI Agents: Cybersecurity’s Evolution
Discover how Cisco security solutions and the four pillars of agentic security protect organizations against autonomous AI risks and evolving threats.
Rogue Behavior: OpenAI Reveals More Model Misalignment Incidents
The AI giant disclosed six examples of concerning model activity and published a new framework for investigating and disclosing such incidents.
Reverse-Engineering Flock Cameras
Hackers captured a Flock camera and got a look (alternate link) at the software: While much of the automatic license plate reader’s (ALPR) most sensitive storage…