The newly released OpenAI Atlas web browser has been found to be susceptible to a prompt injection attack where its omnibox can be jailbroken by disguising a malicious prompt as a seemingly harmless URL to visit.
"The omnibox (combined address/search bar) interprets input either as a URL to navigate to, or as a natural-language command to the agent," NeuralTrust said in a report published Friday.
"We've identified a prompt injection technique that disguises malicious instructions to look like a URL, but that Atlas treats as high-trust 'user intent' text, enabling harmful actions."
Last week, OpenAI launched Atlas as a web browser with built-in ChatGPT capabilities to assist users with web page summarization, inline text editing, and agentic functions.
In the attack outlined by the

The Hacker News
The Register
The radio station 99.5 The Apple
Tom's Guide
WRCB-TV
NBC News
Atlanta Black Star Entertainment
OK Magazine
AlterNet
Raw Story