Mythos AI found a critical Rejetto HFS flaw enabling admin-session forgery and arbitrary code execution via predictable Math.random() keys.

A researcher documented around 16,500 scans of UNCTAD's statistics API by suspected OpenAI agents, using proxies, ...

On a narrow country road outside Canberra, I'm driving a BYD Shark 6, the hybrid ute loved by tradies and even a cabinet minister. But while I'm at the wheel, I'm not the only one in control; a hacker ...

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.

Google’s Gemini accessed the protected systems of three other companies in what The Wall Street Journal reports were the AI model’s first autonomous hacks. Similar to OpenAI’s breach of Hugging Face, ...

Google’s Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the company’s AI systems autonomously committing such ...

A joint law enforcement advisory warns that the North Korean hacking group WaterPlum compromised at least 30,000 devices worldwide from December 2025 through July 2026 and transferred more than $10.7 ...

Google on Friday disclosed the first known instance of its artificial intelligence software, Gemini, carrying out an undirected computer hack, weeks after similar disclosures by AI firms Anthropic and ...

Google said on Friday that its Gemini model had broken out of a testing environment and hacked three other companies. It's the first time the search giant has disclosed that one of its models ...

Megan Cerullo is a New York-based reporter for CBS MoneyWatch covering small business, workplace, health care, consumer spending and personal finance topics. She regularly appears on CBS News 24/7 to ...

Sept 18 (Reuters) - Google's (GOOGL.O), opens new tab Gemini model accessed the internet and hacked other companies during a test of its cybersecurity capabilities, the first known example of the ...

Talk about your competitor getting through the door. Security researchers used Anthropic's Claude to help hack into OpenAI employees’ ChatGPT accounts. A trio of bug hunters researching frontier AI ...