AI Browser Agents Face Critical Security Vulnerabilities, Experts Warn
New AI-powered browsers from OpenAI and Perplexity are facing serious security challenges that could expose users to data theft and unauthorized actions. Cybersecurity experts describe prompt injection attacks as a “systemic challenge” that remains unsolved across the emerging category of agentic browsers.
The Hidden Dangers Behind AI’s Web Browsing Revolution
As OpenAI’s ChatGPT Atlas and Perplexity’s Comet attempt to redefine how we interact with the web, security researchers are sounding alarms about fundamental vulnerabilities that could put user privacy at serious risk. These AI browsers, which promise to automate tasks by clicking through websites and filling out forms on users’ behalf, are facing what experts describe as an unsolved security crisis.