This article outlines Google's advancements in Chrome's security, specifically addressing the risks associated with agentic browsing. It details measures like the User Alignment Critic, origin gating, and user confirmations to combat threats like indirect prompt injection and unauthorized actions. The goal is to ensure user safety while interacting with AI-driven features.

Google Chrome will require user permission by default to access insecure HTTP websites starting with the release of Chrome 154 in October 2026. This change aims to enhance security by encouraging users to connect via HTTPS and reduce the risk of man-in-the-middle attacks. Users will have the option to enable warnings for public or both public and private sites, with the expectation that most websites are already secured with HTTPS.