# Gemini in Chrome Published articles for Gemini in Chrome. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Google Is Testing a Search Bar That Works Outside Chrome DevFeed: [Google Is Testing a Search Bar That Works Outside Chrome]() Original publisher: [Read original article]() Author: Simon Sterne Published: 2026-09-10T16:00:00Z Content type: article Language: en Sources: [Web Designer Depot]() Topics: [Chrome](), [Google](), [Chromium](), [Artificial Intelligence]() Tags: [ai](), [ai-assistants](), [ai-search](), [ai-tech](), [artificial-intelligence](), [browser](), [browser-design](), [chrome](), [chrome-canary](), [chromium](), [everywhere-omnibox](), [future-of-browsers](), [future-of-search](), [gemini](), [gemini-in-chrome](), [google](), [google-chrome](), [google-search](), [project-loom](), [search](), [search-technology](), [ui-design](), [ux-design](), [web-browsers](), [web-design]() ### AI overview Google is testing Project Loom, an experimental floating Search bar that can appear over other Windows apps instead of remaining inside Chrome. The feature is unfinished, with screen sharing, Lens, and AI Mode controls reportedly not yet working. ### Source excerpt Google is quietly testing a way to bring Search outside Chrome and directly on top of whatever app you're using. It's called Project Loom, and this little floating search box could hint at a much bigger future where Google follows you around your desktop. ## Making it easier to understand how content was created and edited DevFeed: [Making it easier to understand how content was created and edited]() Original publisher: [Read original article]() Author: Laurie Richardson Published: 2026-05-17T13:43:50Z Content type: article Language: en Sources: [Google DeepMind News]() Topics: [synthid](), [Artificial Intelligence](), [watermarking](), [Chrome](), [Web](), [Cloud]() Tags: [ai](), [chrome](), [cloud](), [gemini-in-chrome](), [none](), [products](), [synthid](), [watermarking](), [web]() ### AI overview Google DeepMind describes expanded tools for verifying how digital content was created and edited. The update extends SynthID watermark verification and C2PA Content Credentials across Gemini, Search, Chrome, Pixel phones and Cloud, helping users identify AI-generated media and determine whether content is original or modified. ### Source excerpt We're expanding our tools to help you understand how content was created and edited across the web. ## Architecting Security for Agentic Capabilities in Chrome DevFeed: [Architecting Security for Agentic Capabilities in Chrome]() Original publisher: [Read original article]() Author: Google (noreply@blogger.com) Published: 2025-12-08T18:03:00Z Content type: article Language: en Sources: [Google Online Security]() Topics: [agentic browsing](), [Security](), [Chrome](), [prompt injection](), [Artificial Intelligence](), [browsers](), [Google]() Tags: [agentic-browsing](), [ai](), [chrome](), [chrome-security](), [gemini-in-chrome](), [google](), [llm](), [none](), [prompt-injection](), [real-time](), [red-teaming](), [safety](), [security]() ### AI overview Google describes Chrome's layered security approach for agentic browsing, focusing on indirect prompt injection from untrusted web content. The approach includes a User Alignment Critic, origin isolation, user confirmations for critical steps, real-time threat detection, and red-teaming. ### Source excerpt Posted by Nathan Parker, Chrome security team Chrome has been advancing the web's security for well over 15 years, and we're committed to meeting new challenges and opportunities with AI. Billions of people trust Chrome to keep them safe by default, and this is a responsibility we take seriously. Following the recent launch of Gemini in Chrome and the preview of agentic capabilities, we want to share our approach and some new innovations to improve the safety of agentic browsing. The primary new threat facing all agentic browsers is indirect prompt injection. It can appear in malicious sites, third-party content in iframes, or from user-generated content like user reviews, and can cause the agent to take unwanted actions such as initiating financial transactions or exfiltrating sensitive data. Given this open challenge, we are investing in a layered defense that includes both deterministic and probabilistic defenses to make it difficult and costly for attackers to cause harm. Designing safe agentic browsing for Chrome has involved deep collaboration of security experts across Google. We built on Gemini's existing protections and agent security principles and have implemented several new layers for Chrome. We're introducing a user alignment critic where the agent's actions are vetted by a separate model that is isolated from untrusted content. We're also extending Chrome's origin-isolation capabilities to constrain what origins the agent can interact with, to just those that are relevant to the task. Our layered defense also includes user confirmations for critical steps, real-time detection of threats, and red-teaming and response. We'll step through these layers below. Checking agent outputs with User Alignment Critic The main planning model for Gemini uses page content shared in Chrome to decide what action to take next. Exposure to untrusted web content means it is inherently vulnerable to indirect prompt injection. We use techniques like spotlighting that direct