1Password has launched a new browser integration that allows Anthropic's Claude AI to access and use stored security credentials, such as usernames and passwords, without revealing them. This feature, known as 1Password for Claude, enables users to authorize Claude to perform tasks like booking travel or managing online accounts without manually entering login details.
Zero-Exposure Security Framework
The integration is built on a 'zero-exposure security framework' developed by 1Password. This technology works by injecting necessary credentials through a secure channel invisible to Claude. While the AI can use the details, it cannot view passwords or multi-factor authentication (MFA) codes.
User Control and Approval
Access is granted per task, and users can approve or deny requests with a biometric prompt. While this interrupts workflow, it is less cumbersome than manually logging in. After each autofill, 1Password scans the page to ensure no sensitive information is left exposed before returning control to Claude.
The moment an AI agent takes control of the browser, 1Password locks down automatically, limiting access to only the credentials explicitly granted for the current task. Nothing else in the 1Password vault is reachable.
This statement from 1Password underscores the security measures taken to protect user information.
Availability and Future Support
1Password for Claude is currently available to 1Password users on Mac across business, family, and individual plans. To use the feature, users need both the 1Password and Claude desktop apps and browser extensions.
1Password vaults can store various security information, including passwords, passkeys, 2FA codes, API tokens, and personal details like addresses and financial data. Currently, Claude's access is limited to login-related information, but 1Password plans to extend support to payment cards and identity details post-launch.
Source: https://www.theverge.com/tech/966442/1password-anthropic-claude-browser-integration
