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

Source: The Hacker News | Added:

The OpenAI Atlas web browser has a vulnerability that allows prompt injection attacks through its omnibox, which can be exploited by disguising harmful prompts as benign URLs. This issue raises concerns about the security of user interactions within the browser.

---

Impact: OpenAI Atlas

In the Wild: Unknown

Age: Newly disclosed

Remediation: Not specified

Read Full Original Article →