OpenAI’s ChatGPT Atlas Browser Faces Security Threats from Prompt Injection Attacks, Experts Caution
OpenAI’s newly launched ChatGPT Atlas browser contains security flaws that could allow hackers to manipulate the AI into stealing sensitive information or performing unauthorized actions, experts report. The vulnerabilities center on “prompt injection” attacks where malicious instructions hidden on webpages trick the AI system. Security researchers demonstrate how these attacks could compromise user data and accounts.
New AI Browser Introduces Unprecedented Security Challenges
OpenAI’s recently launched ChatGPT Atlas browser contains significant security vulnerabilities that could enable attackers to turn the AI assistant against its users, according to cybersecurity experts. The browser, designed to help users complete tasks across the internet, reportedly faces particular risks from “prompt injection” attacks where hidden commands could manipulate the AI into revealing sensitive data or performing harmful actions.