{ads}

›

ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands

Written By Monday, 27 October 2025 Add Comment



October 27, 2025 at 12:59PM

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

from The Hacker News https://ift.tt/apfWkGt

0 Response to "ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands"

Post a Comment

Subscribe to: Post Comments (Atom)

Article Top Ads

Central Ads Article 1

Middle Ads Article 2

Article Bottom Ads