\n<\/p>\n
Cybersecurity researchers at LayerX Safety<\/a> have recognized a vulnerability in ChatGPT Atlas, the brand new browser from OpenAI, which permits attackers to inject malicious directions immediately right into a consumer\u2019s ChatGPT session reminiscence. The exploit, which they name \u201cChatGPT Tainted Reminiscences,\u201d might enable an attacker to execute distant code, goal a consumer\u2019s account, browser or linked programs, all with out the consumer being conscious. <\/p>\n In accordance with researchers, this vulnerability is especially regarding as a result of ChatGPT Atlas reportedly affords virtually no built-in phishing safety, leaving customers of the browser as much as 90 % extra susceptible than these utilizing customary browsers like Google Chrome or Microsoft Edge. <\/p>\n It\u2019s value mentioning that proper now, the ChatGPT Atlas<\/a> browser is barely accessible on macOS. Variations for Home windows and Android are anticipated to roll out quickly. As for the newly found vulnerability, right here\u2019s what it appears like, why it issues, and what customers can do about it.<\/p>\n When a consumer browses with ChatGPT Atlas, the browser makes use of ChatGPT\u2019s agentic capabilities<\/a> to know net pages, summarise data and act in your behalf. LayerX discovered that an attacker can embed hidden malicious directions into content material that the browser processes. <\/p>\n When ChatGPT interprets that content material as a part of its reminiscence or process checklist, it will probably perform actions the consumer by no means explicitly requested for, opening accounts, executing instructions, and even accessing information.<\/p>\n What\u2019s particularly harmful is that this exploit might persist throughout units or classes as a result of the agentic reminiscence function retains context. An attacker doesn\u2019t want to use a single session in isolation; they might acquire a persistent foothold.<\/p>\n Additionally, because the built-in phishing safety is weak on this new browser mannequin, an attacker can use customary social engineering vectors<\/a> (malicious hyperlinks, hidden prompts) and depend on the browser\u2019s AI agent to do the heavy lifting. Conventional safeguards designed for traditional browsers don’t seem to cowl these AI-agent behaviours.<\/p>\n \u201cThe vulnerability impacts ChatGPT customers on any browser, however it’s significantly harmful for customers of OpenAI\u2019s new agentic browser: ChatGPT Atlas. LayerX has discovered that Atlas presently doesn’t embody any significant anti-phishing protections, which means that customers of this browser are as much as 90% extra susceptible to phishing assaults than customers of conventional browsers like Chrome or Edge.\u201d<\/em><\/p>\n Or Eshed \u2013 Co-Founder & CEO LayerX<\/cite><\/p><\/blockquote>\nHow the vulnerability works<\/strong><\/h3>\n
\n
Why this issues for customers and organisations<\/strong><\/h3>\n