A Chinese-speaking hacker launched cyberattacks that rocked South Korea’s financial sector earlier this month using the ARTEX AI penetration testing suite and Claude agents. The perpetrator targeted several Korean banks, including Shinhan Bank, KB Kookmin Bank and Hana Bank, by exposing customers’ personal and credit card information and in some cases causing system failures. The … Read more
Days after reporters claimed that Meta’s Muse app on the Mac read their private messages — a claim that Meta disputed — Apple announced that it was introducing additional controls over a setting called “Full Disk Access” in macOS. The feature was designed to allow backups to work properly, but now AI agents have added … Read more
OpenAI has confirmed that it is aware of a new security incident in which its AI agents uploaded user-provided images to third-party image hosting services. According to OpenAI, most users were not affected as only 53 incidents were identified where agents accidentally uploaded images to the internet. The disclosure is the result of a broader … Read more
Anthony Albanese says governments must help shape the development of AI, after earlier revealing that an OpenAI agent accessed non-public files on the Australian Medicare data portal. Australian Prime Minister Anthony Albanese has warned artificial intelligence is developing at a “breakneck pace” and called on other countries to shape its development, after an OpenAI agent … Read more
Security researcher Gal Weizman of Forever Security has revealed a new attack technique that can hijack the AI assistants built into popular browsers using a single malicious browser extension. The proof-of-concept, called BragJack, was demonstrated using five Chromium-based browsers or browser assistants: Google Chrome’s Gemini Live, Perplexity Comet, Microsoft Edge, Opera Neon, and Anthropic’s Claude … Read more