ChatGPT Chrome Extension Gains Cross-Tab Browser Control
OpenAI updated the ChatGPT for Chrome extension to enable multi-tab context awareness and cross-page task execution. In Work mode, with user authorization, ChatGPT can directly control the browser to fill forms, send messages, and manage files while reusing logged-in sessions. The feature is available to all users but requires strict permission management due to significant privacy risks.
Full Report
ChatGPT Can Now Operate Google Chrome for You: Read Webpages, Compare Prices, Send Messages, and More
On October 17, it was reported that OpenAI updated the ChatGPT for Chrome extension (version 1.26.1005.11759) on October 15. ChatGPT can now read multiple open tabs in the Chrome browser, answer questions based on webpage content, organize information, or complete cross-page tasks. This feature is available to all users, regardless of whether they have a paid subscription.
When users invoke the browser within a chat, ChatGPT can use currently open webpages as context—for example, comparing multiple product pages, summarizing several documents, or analyzing work files.
According to IT Home’s citation of the blog post, this update also introduces stronger “action” capabilities. In Work mode, ChatGPT is no longer limited to reading webpages; instead, with user authorization, it can control tabs to help users fill out forms, send messages, download files, and organize or group tabs.
Since the extension runs within the user’s standard browser profile, it can reuse login states for websites where the user is already signed in. This allows it to directly assist with workflows in scenarios such as Gmail, LinkedIn, Salesforce, or internal enterprise tools.
However, convenience comes with greater permission requirements. After installing or enabling these capabilities, Chrome may require the extension to read and modify website data, access page debugging tools, manage tabs and downloads, and even read bookmarks, browsing history, or display notifications.
OpenAI stated that these permissions are necessary for ChatGPT to operate the browser, but users can still control its access scope through per-site authorization, allowlists, blocklists, and other methods.
By default, ChatGPT requests confirmation before accessing each new website. Users can choose “Allow once,” “Always allow for this site,” “Always allow for all sites,” or deny access. Notably, “Always allow for all sites” is flagged by OpenAI as a higher-risk option. Additionally, access to browsing history and file uploads/downloads requires separate authorization.