Monday, 27 October 2025

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

iT4iNT SERVER 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 VDS VPS Cloud


http://dlvr.it/TNvYcP
-

No comments:

Post a Comment

Subscribe to: Post Comments (Atom)

Anthropic MCP Design Vulnerability Enables RCE, Threatening AI Supply Chain

iT4iNT SERVER Cybersecurity researchers have discovered a critical "by design" weakness in the Model Context Protocol's (MCP) ...