ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands
ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands 2025-10-27 at 11:36 By 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 […]
ChatGPT Atlas Browser Can Be Tricked by Fake URLs into Executing Hidden Commands Read More »