About Claude in Chrome
Claude in Chrome is Anthropic's browser agent. A side panel lets you describe a task, and Claude reads the page, clicks, types, navigates and fills forms while you watch. Anthropic pitches it at work behind a login with no export button, such as pulling figures from vendor portals, and data entry.
Its safety guidance is the plainest of the official options. Anthropic calls prompt injection the main risk and says the risk "is not zero". It describes two classifiers that screen content and actions, a mode that asks before acting one site at a time, and an "automatically approve" mode with a separate safety check. In internal testing it reports attack success below 0.08 percent, and says that is no guarantee.
The catch is the data and the access. Claude takes screenshots of the active tab and cannot filter sensitive content out, so anything visible joins the conversation. Consumer chats may be used to improve Claude only if you allow it or a chat is flagged for safety review. Where an organisation enables HIPAA it is off by default and outside the business associate agreement. It needs a paid plan, runs only in Chrome and is in beta. Use a separate profile without sensitive accounts, as Anthropic recommends.
Pros and cons
- Made by Anthropic, with a detailed public safety guide
- Asks per site and blocks adult and known pirated sites
- Same Claude, sessions, skills and connectors as its desktop and web apps
- Updated on 31 October 2026
- Needs a paid Claude plan, and is in beta
- Chrome only: Anthropic says other Chromium browsers are unsupported
- Broad access, and it cannot filter sensitive content from what it sees
Permissions
Asks for access to all websites, plus the debugger, tabs, scripting, downloads, identity and native messaging. That lets Claude see and act on pages and link to the desktop app, with Claude's own per-site approvals on top.
