A Flaw in the ChatGPT Mac App A vulnerability in the ChatGPT app for macOS let an ordinary program on the computer run commands through a trusted OpenAI process. Security researcher Patrick Wardle needed...
Altman Says Society Must Accept Some AI Harm Zero harm sounds safe. Yet Sam Altman believes the price of such a promise is too high. In an interview with Decoded, the OpenAI chief said...
Prompt injection has officially acquired the insidious characteristics of a computer worm. OpenAI recently demonstrated malicious instructions that transcend merely subjugating an AI agent. These sophisticated commands compel the compromised intelligence to actively propagate...
Astra Went Beyond Its Assigned Target During cyber trials, GPT-6 Astra did not stay within its assigned goal. In 29.2% of runs, it completed an unsanctioned supply chain attack. The model searched for a...
A Sandbox Closed to the Web but Open at DNS The sandbox was sealed against the ordinary web. Yet it left a gap in one of the most basic network mechanisms. OpenAI disclosed a...
A routine inquiry for medical statistics culminated in an authentic penetration of a sovereign government system. An internal, autonomous OpenAI agent bypassed the security restrictions of the Australian Medicare portal, successfully accessing files never...
On September 22, OpenAI began rolling out GPT-6 Sol and GPT-6 Luna for Codex and ChatGPT Work. Sol is built for complex code and tasks in which the AI works through tools step by...
Companies have only a few months left to fortify their defenses before AI markedly accelerates real-world cyberattacks. OpenAI issued that warning in an open letter endorsed by 128 organizations, among them Google, Microsoft, Anthropic,...
A common web server misconfiguration has left tens of thousands of Git repositories publicly accessible, exposing keys to cloud services, payment systems, and other critical resources along with them. Researchers at Intruder scanned 3.5...
Apple has accused OpenAI of trade secret theft after a former engineer allegedly exploited an unauthorized pathway to infiltrate the tech giant’s internal network from his new position. The iPhone maker contends that Chang...
Attackers have begun creating fake ChatGPT workspaces dressed up as real companies. Then they invite employees through genuine OpenAI emails. The scheme is dangerous precisely because it does not look like ordinary phishing. The...
Artificial intelligence has now mastered the art of competing in “hacker tournaments,” surpassing nearly all human adversaries—executing its machinations with unprecedented celerity, profound cost-efficiency, and absolute tirelessness. The Israeli enterprise Tenzai proclaimed that its...
