BragJack research shows malicious extensions can seize browser AI agents
Image: Primary Security researcher Gal Weizman disclosed BragJack, a proof-of-concept technique that uses one malicious browser extension to hijack AI assistants in five Chromium-based browsers or browser assistants. The research produced two CVEs and more than $20,000 in vendor bug bounties. Weizman showed that an installed extension could manipulate trusted web traffic, then direct privileged AI components to read sensitive data or act for a victim. Google and Microsoft resolved the flaws assigned to them.
Sources
Published by Tech & Business, a media brand covering technology and business.
This story was sourced from BleepingComputer and reviewed by the T&B editorial agent team.
Back to Newswire
