1Password lets Claude AI use your passwords without ever seeing them via new zero-exposure framework

1Password Will Let You Allow Claude to Use Your Passwords, but Not See Them

Blake has over a decade of experience writing for the web, with a focus on mobile phones, where he covered the smartphone boom of the 2010s and the broader tech scene. When he's not in front of a keyboard, you'll most likely find him playing video games or watching horror movies. Claude can now securely log you into sites like Audible and Stripe thanks to a new partnership between 1Password and Anthropic. Announced on Thursday, the new integration will allow Claude to access your password credentials without having it actually see the passwords. 1Password says this is the first browser integration to allow agents to access credentials without granting direct access. The "zero-exposure" method requires you to manually approve logins every time via biometric approval. The tech world is increasingly steering toward agentic AI, in which an AI agent can perform tasks on your behalf. But there are glaring privacy and security concerns about handing your sensitive information to AI. This is just one of what will likely be a series of privacy- and security-focused agentic tools that will make it easier for you to use AI for yet another part of your life if you let it. The new integration allows agents to use your stored credentials from 1Password, but your passwords are never passed onto the model itself. 1Password showed the tool in action in a video that used it to access Audible and ask Claude to find a new audiobook based on the user's wishlist. Another security measure is Agentic Mode: When an agent takes over to complete a task for you, 1Password will lock down automatically, and the agent will only be able to use logins and codes previously provided for that specific task. CNET's resident password manager expert, Joe Supan, expressed cautious praise for the new tool, saying, "I would normally be very wary about giving an AI agent access to my password manager, but 1Password seems to have several good guardrails in place, namely requiring biometric authentication for each login." 1Password for Claude is now available on Mac for business, family and individual plans. Detailed instructions for setting up the integration are available on the 1Password website. You'll need the 1Password desktop app and browser extension, as well as the Claude desktop app and browser extension, to get started. In its current form, the new tool only handles passwords, but 1Password plans to integrate payment cards and identity details in the future.

Claude can now use your 1Password credentials for you

1Password has launched a new browser integration for Claude that allows the Anthropic chatbot to access stored security credentials like usernames and passwords. The 1Password for Claude feature means that users can authorize Claude to complete multi-step tasks like booking travel and managing online accounts on their behalf without having to manually input their login credentials, but without actually exposing your security information to Anthropic's AI models, according to 1Password. That's made possible by a new "zero-exposure security framework" developed by 1Password, which works by injecting the required credentials for each task through a secure channel that the Claude agent can't view. That means that while the AI can be granted permission to use your stored details, it can't actually see your passwords or MFA one-time code. Claude access is granted per task, and 1Password says its users can approve or deny each request with a single biometric prompt. That's still a workflow interruption, but less of a nuisance compared to temporarily taking over to sign into accounts. As a precaution, 1Password says it also scans the page after every autofill to ensure nothing in form submissions remains 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," 1Password said in its press release. "Nothing else in the 1Password vault is reachable." 1Password for Claude is available now for 1Password users on Mac, across business, family, and individual plans. The 1Password desktop app and browser extensions are required to use the feature, as well as the Claude desktop app and browser extensions. You can store a wide variety of security information in 1Password's vaults, including passwords, passkeys, 2FA codes, API tokens, and personal information like your address and financial details. 1Password doesn't specify which credentials Claude will be able to access, but it appears to be limited to login-related details for now -- the company says that support for payment cards and identity details will be available sometime after launch.

1Password's new Agentic Mode lets Claude log into your accounts without seeing your credentials

Follow ZDNET: Add us as a preferred source on Google. ZDNET's key takeaways * Claude can use protected accounts without seeing credentials. * 1Password injects passwords and MFA codes outside the AI. * Agentic Mode launches first with Claude, with more agents ahead. As I've been working with Claude Cowork and ChatGPT Work, I've found real, tangible time-saving opportunities that both tools offer. While it's not possible to delegate everything to these AI agents, some tedious tasks are perfect to assign to the digital members of my team. But there's a gotcha. Most of what I do online, especially those activities that have some administrative component, is locked behind a login of some kind. Also: I let ChatGPT Work and Claude Cowork loose on my files - only one made me nervous Whether it's Stripe for managing payments, my web hosting provider, my other web hosting provider, my yet another web hosting provider, my accounting system, or even my list management app, they're all secured behind a login system. The challenge, then, is what actual actions you can take when you charge up your courage enough (or maximize your laziness or overwhelm enough) to delegate a project to an AI. How can you set an AI loose on a project without giving it complete access to your protected resources? 1Password points the way Password management giant 1Password thinks it has a solution. The company announced today that it has built an integration with Claude that allows Claude to request access to services from 1Password. The key idea here is that Claude never sees the password. Instead, Claude requests a password, 1Password offers up an authorization sheet that requires approval, and then those credentials are filled in at the desired destination site -- all without Claude ever getting access to a single password or authentication code. The company provided two examples of this access. In one, a manager uses Claude via 1Password to sift through Stripe transactions to find any red flags. In the other, an Audible user uses Claude via 1Password to find audiobooks that might prove to be a good listen. Also: Don't let an AI chatbot pick your password, ever I can certainly see the benefit of using Claude to help do some financial forensic accounting, even if I'd still be worried about letting Claude have access to my Stripe account. But looking for an audiobook recommendation? I recognize this is just a demo, but using the AI to help you use up your Audible credits seems ... unnecessary? Disappointing? Overkill? In any case, the point is that Claude never gets access to your account credentials. I was concerned about repeat access, so I asked the company, "So how do you make sure, if you let it go into Stripe once to check something, that it won't just randomly go there again? You've now just given it access to your entire income-producing section, for example." I was told, "This concern is exactly what 1Password for Claude was designed to solve. Access is granted per session, scoped to a specific task, and does not carry over. There is no standing access." It was explained to me that when Claude wants a credential, it asks for access for the one task it's currently working on. The user is asked for approval. According to the company, this can be done with biometric verification, a password, or Touch ID. YubiKey is generally supported in 1Password, but it's not yet available for this application, although I'm told that it's planned. Upon completion of the task, authorization ends. The company told me, "If the agent goes back to Stripe a second time, it cannot simply reuse the earlier permission. It has to request access again, and the user has to approve it again." Also: I gave Claude Cowork 7 non-coding jobs, and it earned a spot in my toolbox That might be a bit optimistic. Many sites grant ongoing access via cookies or other means once access has been secured. In practice, the session is likely to persist the way any browser session would after a sign-in. From the release, this workflow didn't seem entirely complete, so I asked for more clarification. I was unofficially told that the need for reauthentication applies as long as you log out at the end of the first session. The key to this would be prompting Claude with something like, "Log in to Stripe, give me my current revenue, and log out when you're done." At that point, if you do need to be logged in again, you would receive a new authorization prompt. Claude won't simply reuse the earlier permission. That said, Claude won't return to the site on its own. 1Password says Claude will only return with clear instructions from the user. Technically, this access is supported by 1Password's new Agentic Mode, which "activates automatically the moment a recognized AI agent takes control of the browser." 1Password says that when Agentic Mode is on, the agent can only reach those credentials specifically granted for the current task. No other vault-stored passwords are available through the browser. I was told, "So, to answer your question directly: granting access once to check something in Stripe does not open the door to your vault. It opens a window for one specific task, and 1Password closes it when that task is done. And throughout that entire task, Claude never sees the credential itself. The password and the MFA one-time code are injected directly into the page by 1Password through a secure channel, outside the agent's view. They never reach the model, Claude's context, or Anthropic's systems at any point." Availability According to the company, Agentic Mode will be available to all 1Password users as of today. I was told, "While credential [controls] will be available on day one, future support for payment cards and identity details in 1Password will be available after launch." The company also says, "Agentic Mode activates automatically and runs quietly in the background. Users can see when it is active directly in the 1Password browser extension, with the option to cancel it at any time. Starting with Claude, the underlying framework is designed to extend to any browser-based agent or platform as the ecosystem grows." Also: 5 security tactics your business can't get wrong in the age of AI - and why they're critical Random factoid: Superhero actors Robert Downey Jr. (Iron Man) and Ryan Reynolds (who played Deadpool and the Green Lantern, but we won't hold that against him) are investors in 1Password. Would you trust Claude to access your Stripe account through 1Password? Let us know in the comments below. You can follow my day-to-day project updates on social media. Be sure to subscribe to my weekly update newsletter, and follow me on Twitter/X at @DavidGewirtz, on Facebook at Facebook.com/DavidGewirtz, on Instagram at Instagram.com/DavidGewirtz, on Bluesky at @DavidGewirtz.com, and on YouTube at YouTube.com/DavidGewirtzTV.

You can now grant Claude access to your 1Password credentials - Engadget

1Password promises your login information will never interact with Anthropic's AI, or its servers. If you like putting Claude's AI agents to work on personal chores but are concerned about giving them access to your credentials, there's a new solution available. 1Password just announced 1Password for Claude, a new feature on its browser extension that lets Claude use your credentials, but blocks your private info from reaching the model, its memory or Anthropic's systems. "Users can now authorize Claude to complete real-world tasks like booking travel and managing accounts securely with credentials injected directly to the target system on their behalf," 1Password explains. Security has emerged as a big issue when using agents to complete tasks on your behalf. Sharing credentials directly with an agent exposes them to the model, its memory and the systems behind it, which can pose a risk if the model gets hacked. To solve that problem, 1Password built a "zero-exposure security framework" that allows agents to use stored credentials from your 1Password vault without them reaching the model. Access is granted per session, limited to specific, approved items and not carried over. Since passwords and one-time MFA codes are injected through a secure channel managed by 1Password, they stay outside the model. At the same time, 1Password allows authenticated multi-site sessions to complete multi-step workflows without prompting the user for credentials at each step. For extra security, 1Password locks down when an AI agent takes control of your browers, limiting access to only the credentials explicitly granted for the current task. Finally, 1Password also scans pages after every autofill to ensure no secrets remain exposed. Along with the Claude integration, 1Password introduced a new Agentic Mode for all 1Password users that will safeguards credentials against active agents. When it detects one, 1Password locks down, so the agent can only find passwords explicitly granted for the current task. Users will also see that this security feature is active directly in the 1Password browser extension. This will only work with Claude at first, but will expand to other agents "as the ecosystem grows," 1Password said. 1Password for Claude is now available to 1Password users on Mac for business, family and individual plans. Getting started requires the 1Password desktop app and browser extensions, plus the Claude desktop app and browser extensions. "Future support for payment cards and identity details will be available after launch," according to 1Password.

1Password lets Claude log you into websites without ever seeing your passwords

1Password for Claude lets the AI agent use your logins via biometric approval without the credentials ever reaching the model or Anthropic's systems. 1Password has launched a browser integration that lets Anthropic's Claude use stored credentials to complete tasks on the web without the passwords ever reaching the AI model, according to a blog post published on Thursday. The company calls it a zero-exposure architecture: when Claude needs to sign in, 1Password shows the user which credential is being requested and why, then waits for biometric approval before injecting the login directly into the page. Claude never sees the vault item, password, or one-time code, and access ends when the task is complete. The integration addresses a fundamental tension in agentic AI. Browser-based agents like Claude can navigate websites, fill out forms, and complete purchases, but reaching a login page has historically forced users to either hand over their password or take the wheel themselves. 1Password says this is the first browser integration that lets an agent use credentials without granting direct access to them. After autofill, 1Password checks whether secrets were exposed on the page. If submission fails, the extension clears the filled values before returning control to Claude. The credential stays encrypted and controlled by 1Password throughout the process. The launch also introduces Agentic Mode, a feature in the 1Password browser extension that automatically locks down the vault when a compatible AI agent takes control. The agent can only use logins and one-time codes explicitly approved for the current task, and the rest of the vault stays out of reach. Agentic Mode activates even if the 1Password-Claude integration is not configured, and supports agents beyond Claude. The timing is notable given that security researchers recently demonstrated how AI browsers could be tricked into leaking user credentials through prompt injection attacks, with Anthropic's own Claude extension among those affected. 1Password CTO Nancy Wang said in the company's announcement that the answer is not handing agents your secrets, but letting a user give an agent permission to use a credential without letting the agent see it. She called that distinction the foundation of trust in AI agents. 1Password for Claude is available now on Mac for business, family, and individual plans, and requires the 1Password desktop app, browser extension, Claude desktop app, and Claude browser extension. The company, which recently acquired Israeli startup Apono to govern AI agent access inside enterprise systems, said it plans to add support for payment cards and identity details after launch. CNET's password manager expert Joe Supan said he would normally be very wary about giving an AI agent access to his password manager, but that 1Password appears to have several good guardrails in place, particularly biometric authentication for each login. The integration marks the first time a major password manager has built a dedicated secure channel for an AI agent to use credentials at runtime, rather than exposing them to the model's context. Whether the approach holds up against the kind of prompt injection attacks that have already compromised AI browsers remains to be seen.

Claude did my FreshDirect shopping, with help from 1Password

Testing showed successful FreshDirect order completion, demonstrating potential for streamlining routine online chores, though social logins and passkeys aren't currently supported. AI agents doing our grocery shopping? I've heard that promise before, and up until now, it's been an empty one. But thanks to a new integration with 1Password, the popular password manager, Claude just did my weekly FreshDirect shopping, all without me ever touching a web browser. Announced just today, Claude's 1Password connector lets Claude log into websites using your stored 1Password credentials. The key is that Claude never actually sees your passwords; instead, when it needs to sign into a website, Claude pings the 1Password connector, and 1Password handles your login info using a separate channel that Claude never sees. To further protect your secret 1Password information, a new Agentic Mode locks down the 1Password extension for Chrome, ensuring that Claude (which browses the web using its own Chrome extension) can't click on it. Before going any further, two important caveats: Claude's 1Password connector doesn't support social logins (like "Sign in with Google"). Also, passkeys aren't supported either (or at least not yet, 1Password says). To test Claude's new 1Password abilities, I fired up the Claude Desktop app (for now, you must use Claude Desktop for Mac), clicked Customize > Connectors, added the 1Password connector, and authorized it. And if you haven't done so already, you'll also need to install the Chrome extensions for Claude and 1Password. Next, I went to Claude Cowork, and gave Claude a prompt: "Can you browse to FreshDirect and sign in?" (I chose FreshDirect because it's a shopping site I use regularly, and I have a weekly delivery spot, which gives me a few days to edit Claude's choices.) Claude began navigating in Chrome, eventually hitting the login portal. Claude directed 1Password to enter my username (I had to give Claude's 1Password connector permission to use my FreshDirect credentials), then told me that a six-digit authorization code was incoming. I entered that code into a separate modal that Claude couldn't see, and then -- success: You're signed in to FreshDirect (account: Benjamin), with your weekly Saturday 7-9 AM delivery slot showing. This is where the fun started. While I love FreshDirect as a service, I hate its finicky website. Letting Claude do the searching and clicking was, in a word, heaven. "OK," I told Claude, "can you go to the 'reorder' section and suggest 10 items to add to my cart?" It did (milk, scallions, strawberries, cucumbers, shrimp, and more), I approved them, and boom -- they were in my shopping cart. Upping the ante, I gave Claude a recipe for barbecue chicken, asked for side suggestions (potato salad, corn bread), and then we talked over ingredients, discussing what I had on hand and what I needed. Claude came up with a shopping list (potatoes, cabbage, carrots, and so on), and I gave the go-ahead, allowing Claude to handle the rest: Adding the whole-stalk Ocean Mist Farms Celery, the top result ... Added celery to the existing order ... Good, cabbage confirmed at quantity 1. Now searching for carrots.... About five minutes later, it was done: Order updated -- chicken leg quarters, gold potatoes, green cabbage, carrots, celery, red onion, and bread & butter pickle chips are all added, bringing the new total to $109.60 for Saturday's 7-9 AM delivery. You're all set for oven BBQ chicken with coleslaw and potato salad, and you can still tweak anything before Friday 11:45 PM. A few minutes later, a receipt popped up in my email. The order looked good, and I checked my weekly FreshDirect to-do item off my list. Now, Claude's new 1Password connector is about passwords, not grocery shopping. But the ability for Claude to use 1Password to log into websites as me unlocks all kinds of interesting possibilities, like a weekly routine where Claude does a first-pass on my FreshDirect cart, allowing me to go in later and look over its picks. Would I let Claude pay my online credit card bills, or log into my checking account? Ah, no. Would I let Claude and 1Password take FreshDirect off my plate? You bet.

1Password now lets Claude sign in to websites without seeing your passwords

1Password is launching a new Claude integration for Mac users today. It's designed to let Anthropic's AI agent sign in to websites without seeing your password or two-factor authentication code. 1Password for Claude arrives on Mac, here's how it works 1Password for Claude lets you authorize Claude to complete browser-based tasks that require an account login. This is useful for things like booking travel or managing online accounts. According to 1Password, approved credentials are delivered through a secure channel and injected directly into the destination page. The password, one-time code, and other secrets never enter Claude's context, memory, or Anthropic's systems. Instead of granting ongoing access to a vault, Claude requests the specific login items it needs for a task. The user can approve or deny that request with a biometric prompt, and the permission lasts only for the current session. 1Password can also broker access across multiple websites during the same task, allowing Claude to complete a multi-step workflow without stopping for a new login each time. 1Password Agentic Mode The launch also introduces what 1Password calls Agentic Mode. When a compatible AI agent takes control of the browser, the 1Password extension automatically locks down the vault so that only the credentials explicitly approved for that task remain available. Users can see when the mode is active and cancel it at any time. 1Password says it also analyzes the page after each autofill. If a form submission fails, any filled values are wiped before control returns to the agent. Availability 1Password for Claude is available now to Mac users on business, family, and individual plans. It requires the 1Password desktop app and browser extension, along with the Claude desktop app and browser extension. Support for payment cards and identity information is planned for a later update. The Anthropic partnership was first outlined in March, when 1Password said Claude would gain consent-based access to vault items. This release turns that plan into a shipping Mac feature, while laying the groundwork for similar integrations with other browser-based AI agents. With iOS 27 and macOS 27, Apple has its own modest password reset feature that uses AI behind the scenes as well. You can learn more about 1Password's new Claude integration here.

1Password for Claude Lets AI Log In Without Seeing Your Passwords

Popular password management app 1Password today added Claude support, which means AI service Claude can access credentials stored in 1Password for completing browser tasks. When Claude wants to sign in to a website, 1Password shows the user which credential Claude wants access to and why. After the user approves the request, 1Password adds the credential directly to the page. Access is limited to the current task and ends when the task has been completed. The 1Password team says that after a password is autofilled, the app checks to make sure secrets were not exposed on the page. Credit cards and identities in 1Password are not supported at the current time, so Claude's access is limited to logins and one-time codes. The 1Password browser extension is also being updated with Agentic Mode, which gives users control over browser-based AI agents. When an AI agent takes over, the 1Password extension locks down so passwords are not exposed. The password interface is hidden, and the agent can use logins and one-time codes only when the user gives approval. Agentic Mode works to protect passwords from AI agents even if the integration is not set up. 1Password for Claude is available for Mac, and 1Password business, family, and individual plan subscribers can use it. A Pro, Max, Team, or Enterprise Claude plan is required. 1Password has a help document with detailed information on how to set it up. Claude can use 1Password logins across sites where Claude in Chrome can complete actions. The 1Password desktop app and browser extension are required, as are the Claude desktop app and the Claude in Chrome browser extension.

1Password now lets Claude log in to sites without seeing your passwords -- use these 7 prompts to test this new feature

Your online safety is secure with this new Claude integration There is such a thing as giving up too much of your personal information to a chatbot. Letting a chatbot know all about your bank account, giving it the names of your closest friends & family members and exposing it to your current address just isn't the way to go. But there is a long list of AI password managers that store, protect, and automatically change your passwords to keep you safe from any sort of hacks & scams. While 1Password may not be powered by AI, it handles the same tasks as those aforementioned password managers while also auto-filling login credentials across all your devices and generating strong, unique passwords for the sites you regularly visit. Speaking of AI, 1Password and Claude have now joined forces to not only ensure your online safety stays intact, but also to handle everyday tasks for you that require your login credentials. And best of all, Claude won't ever actually see your passwords whenever it's logging into your sites to handle whatever job you've just given it. Say hello to 1Password for Claude Now that 1Password is capable of working in conjunction with Claude, here's how it works: whenever Claude is given a task that requires it to sign in, 1Password notifies its users about which credential is being requested by the chatbot and why. After a user approves Claude's login attempt, 1Password enters the password and makes sure to never expose it to Claude. Claude is only concerned with completing the job you've given it, while 1Password works simultaneously to check that your credentials have not been compromised. To take advantage of this new feature, you must own a Mac device and have access to 1Password's business, family, or individual subscription plan. Enabling it means your device has to have the 1Password desktop app, the 1Password browser extension, the Claude desktop app and the Claude in Chrome browser extension. You can take a look at these detailed directions on how to make good use of this new feature. 1Password is obviously aware of its users' fears concerning browser-based AI agents taking over and possibly seeing the login details stored in their 1Password account. In an official blog post posted by the company, it made mention of a new "Agentic Mode" that's meant to keep you safe should this ever happen. "When a compatible AI agent takes over, the 1Password extension automatically locks down," the blog explained. "The interface is hidden, and the agent can only use the logins and one-time codes explicitly approved for the current task. The rest of the vault stays out of reach." Some of the examples 1Password provides for their new Claude integration include the chatbot logging in to handle your booking travel duties, presenting you with a Stripe revenue summary and redeeming your credits on Audible. I hopped into Claude and asked it to come up with the sort of prompts that act as tasks for the chatbot that require it to act on a site it needs to log into on your behalf: * Check my Audible wishlist and redeem this month's credit on whichever title has the best reviews. * Log into my [name of airline] account and check if my seat can be upgraded with my frequent flyer miles. * Go to [name of electric company's site] and see if my bill went up this month. * Compare prices for [name of item] across the sites I have accounts on, then order from whichever is cheapest. * Update my shipping address on my [name of online retailer] account. * Pull a revenue summary from my Stripe dashboard and flag anything unusual. * Check my business bank account for any suspicious transactions this week. Bottom line 1Password for Claude sounds and looks like a trustworthy proposition since it goes out of its way to complete any sort of tasks that require a sign-in and make sure your passwords are never exposed to AI. The password manager company will release details about payment cards and identity details sometime after launch. Follow Tom's Guide on Google News and add us as a preferred source to get our up-to-date news, analysis, and reviews in your feeds. Subscribe to Tom's Guide on YouTube and follow us on TikTok.

Claude can now enter all your passwords for you - if you give it permission

* 1Password unveils Claude partnership, letting Anthropic's AI authenticate on users' behalf via zero‑exposure architecture * Users approve each login with biometrics * New Agentic Mode in the browser extension locks down the interface when AI agents take over Top password manager company 1Password has launched a new tool that allows artificial intelligence assistant Claude to authenticate on behalf of their user, and thus complete assignments that were previously impossible without major security tradeoffs. 1Password for Claude is built on "zero-exposure architecture" - so in practice, it means Claude can essentially ask 1Password to complete the sign-in process, but it will never see the credentials, and they will never be loaded into its memory. In turn, 1Password will notify the user, and will request biometric approval before proceeding. Once granted, it will autofill the credentials and check to see if they were exposed on the page or not. If submission fails, it will clear the filled values and report back. Agentic Mode "We need a new security model that is purpose-built for agents, not just humans," said Nancy Wang, CTO of 1Password. "The answer isn't handing agents your secrets. It is to let a user give an agent permission to use a credential without letting the agent see it. Claude knows it used your login; it does not need the password or one-time code in its context. That distinction is where trust in agents starts and the foundation we're building with Anthropic." To further strengthen its security posture, 1Password also announced Agentic Mode, a new feature in the browser extension that gives users visibility and control over browser-based AI agents. When a compatible AI agent takes over, the 1Password extension automatically locks down and hides the interface. The agent can only use the logins and OTPs explicitly approved for the current task. Even if the integration is not set up, and even if 1Password is not required for the current agentic task, Agentic Mode works, the company stressed. Other agents, besides Claude, are supported, as well. Currently a major debate is ongoing, about how much permissions AI agents should receive, and under what rules. We've already seen horror stories of AI agents deleting people's entire email inboxes, or otherwise ruining days of hard work. Whether or not this picks up or most people remain skeptical about giving AI access to certain services, remains to be seen. Follow TechRadar on Google News and add us as a preferred source to get our expert news, reviews, and opinion in your feeds.

1Password lets Claude inside your accounts without handing over the keys

Claude can now sign in on your behalf while your password stays hidden, though trusting it after login is a separate decision 1Password is giving Claude a way into your online accounts without making your passwords part of the bargain. The new 1Password for Claude integration can fill login details while keeping the credentials hidden from Anthropic's AI agent. Available now on Mac, the feature kicks in when Claude reaches a sign-in page during a task. Claude requests a saved login, then you approve or deny it. If approved, 1Password submits the credentials through a separate encrypted channel. Passwords and one-time codes never enter Claude's context or Anthropic's systems. How does 1Password keep Claude out Claude identifies the website and asks for access, but it receives only basic information about the approved login and whether the attempt worked. The 1Password browser extension decrypts and inserts the password while Claude temporarily stops reading the page. Agentic Mode also switches on whenever Claude takes control of a browser tab. It removes 1Password's usual autofill interface and limits the agent to vault items approved for that session. If the submission fails, the extension clears the credentials before Claude regains control. There's no half-filled form waiting for an inquisitive AI to inspect. Where does that protection end These safeguards cover how credentials are approved and delivered. Once Claude successfully signs in, it can operate inside the account as an authenticated user. What happens next depends on Claude's controls and whatever that website allows it to do. Recommended Videos Keeping a password away from the model closes one obvious security hole. It doesn't make every action after login harmless. You'll still need to consider the task and what Claude could view or change inside that account. A secure login solves the credential problem, not the trust problem. Who can use it now 1Password for Claude is available to individual, family, and business subscribers using a Mac. It requires version 8.12.28 or later of the 1Password desktop app and browser extension, plus Claude's desktop and browser extensions. Business administrators must enable agentic autofill before employees can connect it. The first release works with usernames, passwords, and one-time codes saved as login items. Passkeys and social options such as Sign in with Google aren't supported yet. Start with a tightly defined task on a low-risk account before giving Claude access to anything that could become expensive, public, or painful to undo.

1Password brings secure credential access to Anthropic's Claude

1Password brings secure credential access to Anthropic's Claude Identity security company 1Password today launched 1Password for Claude, a browser integration that lets Anthropic PBC's Claude use a person's stored logins to complete online tasks without those credentials ever reaching the artificial intelligence model. The tool targets a problem that has grown as AI agents begin acting on people's behalf. To let an agent sign in somewhere, users have generally had to paste credentials straight into the agent's context, where the model can read them. The other option was stopping to authenticate by hand at every step. 1Password for Claude drops that tradeoff. Credentials are injected into the target site through a secure channel that 1Password controls, and the password and any multifactor onetime code stay outside the model, its memory and Anthropic's systems. Access is granted per session and scoped to a set of approved items. It does not carry into other sessions and it leaves no standing access behind. Claude requests the credentials it needs for a given task and the user approves or denies each request with a single biometric prompt. "We need a new security model that is purpose-built for agents, not just humans," Chief Technology Officer Nancy Wang said in the announcement. "The answer isn't handing agents your secrets. It is to let a user give an agent permission to use a credential without letting the agent see it." The integration runs on what 1Password calls a zero-exposure security framework. Alongside it, the company is introducing a feature called Agentic Mode for all users. The moment a compatible agent takes control of the browser, the vault locks down. Only the credentials granted for the current task stay reachable. Nothing else is accessible. Agentic Mode turns itself on and stays active while an agent works. Users can see it running in the 1Password browser extension and switch it off whenever they want. Two other features fill out the release. 1Password brokers credential access across multiple sites inside one task, so Claude can move through multistep workflows without asking for logins again. It also scans each page after every autofill and wipes any filled values if a form submission fails, cutting off a common way for secrets to linger on screen. 1Password says Agentic Mode starts with Claude and is built to extend to other browser-based agents as the market grows. 1Password for Claude is available now to 1Password users on Mac across business, family and individual plans. It requires the 1Password desktop app and browser extensions along with the Claude desktop app and browser extensions. Support for payment cards and personal details such as names and addresses is due after launch. The company's enterprise vault holds more than 1.5 billion credentials and secrets and is used by more than 1 million developers and 180,000 businesses, including Figma Inc., GitHub Inc., MongoDB Inc., Notion Labs Inc., Perplexity AI Inc., Salesforce Inc. and Stripe Inc.

This AI Can Now Log Into Websites for You. But Should You Let It?

Claude is teaming up with a popular password manager to help your AI agent complete tasks without exposing your credentials to the LLM. Through 1Password for Claude, you can now authorize your AI agent to enter your credentials using 1Password, a password manager that works via an extension in your browser. For instance, if you want your AI agent to book flight tickets, it could easily go into the browser and enter your travel dates and destination, but it might get stuck when it tries to log into your account on the travel site. Most people are skeptical about handing over their credentials to an AI agent -- and rightfully so -- and that's where 1Password comes in, providing users a "secure, easy way for agents to use credentials without exposing them." An announcement from 1Password adds that the task is carried out without credentials "ever reaching the model, its memory, or Anthropic's systems."

1Password Brings Secure Website Logins to Claude AI on Mac

* Claude signs in without viewing stored passwords * Biometric approval authorises every login request * Agentic Mode restricts AI access to approved credentials 1Password has launched a new integration for Anthropic's Claude AI that allows the chatbot to sign in to websites using credentials stored in a user's 1Password vault without exposing passwords or one-time passcodes. The feature, called 1Password for Claude, is designed for browser-based AI tasks that require access to accounts. Alongside the integration, the company has also introduced Agentic Mode, a browser extension feature that limits AI agents to using only the credentials approved by users for a specific task. 1Password Adds Secure Claude AI Integration for Browser-Based Tasks According to the 1Password blog, users can authorise Claude to access websites that require sign-in while 1Password manages the login process. Each request requires biometric approval before the extension securely fills the required credentials into the webpage. The stored login details remain within 1Password and are not shared with Claude or Anthropic's infrastructure. Access is limited to the active task and automatically expires once it is completed. After autofill, the extension checks that credential data is no longer visible on the webpage. If a sign-in attempt fails, it clears the entered details before ending the session. The company has also rolled out Agentic Mode for the 1Password browser extension. It automatically activates when a supported AI agent takes control of the browser, restricting access to only the credentials approved for the current task and keeping the rest of the user's vault inaccessible. According to 1Password, the feature works even when the Claude integration is not enabled and is designed to support additional AI agents in the future. The integration is intended for browser automation tasks that require account access. For example, 1Password said Claude can sign in to services such as Audible to redeem audiobook credits or to a Stripe account to generate a revenue summary after receiving user approval. The company said the Claude integration is part of its broader effort to build secure access controls for AI agents across browsers and developer tools. It previously introduced its MCP Server for managing developer credentials and plans to extend the same approach to other AI-driven workflows. 1Password for Claude is currently available to Mac users on the Business, Family and Individual plans. It requires the 1Password desktop application and browser extension, as well as the Claude desktop application and browser extension. Support for payment cards and identity information will be added in a future update.

1Password and Anthropic Bring Secure Credential Access to Claude | PYMNTS.com

The browser integration, 1Password for Claude, is designed to let users authorize Claude to complete tasks such as booking travel and managing accounts, while preventing the model from seeing the credentials as well as retaining control over when and why the credentials are used, 1Password said in a Thursday (July 16) press release. For example, an everyday AI user can have Claude redeem credits on Audible, and a small business owner can have Claude provide a Stripe revenue summary. In each case, the agent can perform the task without seeing the user's credentials, 1Password said in a Thursday blog post. "Claude knows it used your login; it does not need the password or one-time code in its context," 1Password Chief Technology Officer Nancy Wang said in the press release. "That distinction is where trust in agents starts and the foundation we're building with Anthropic." 1Password for Claude is now available to 1Password users on Mac. The company plans to extend this solution to additional browser-based agents and platforms, and to add support for payment cards and identity detailer, according to the release. The PYMNTS Intelligence report "2026 Global Digital Shopping Index: The Agentic Commerce Deep Dive" found that the willingness of consumers to delegate to AI agents varies by task. While 56% of consumers will let an agent search and compare products on their behalf, fewer than 40% will let one touch their payment credentials, according to the report. "Still, most consumers say they would let agents make purchases for them if the right guardrails are in place," the report said. Another PYMNTS Intelligence report, "The Prompt Economy™: Tokens, Trust and Transactions," found that the impact of agentic commerce introduces new possibilities for how consumers and merchants interact. The report also found that payment networks and other payment service providers are building developer tools and solutions that bring tokenized payments into AI environments to facilitate agentic commerce. "These solutions take different forms, but the goal is the same: Make tokenized, network-level payments accessible to AI systems while enhancing personalization and security for consumers and merchants," the report said. For all PYMNTS AI and digital transformation coverage, subscribe to the daily AI and Digital Transformation Newsletters.

1Password And Anthropic Bring Secure Credential Access To Claude

1Password announced 1Password for Claude, the first browser integration that gives Claude access to stored credentials without those credentials ever reaching the model, its memory, or Anthropic's systems. The launch marks a critical new step in securing agents that do real work. It gives them the access they need to complete tasks while keeping people in control of which credentials are used, when, and for what purpose. Users can now authorize Claude to complete real-world tasks like booking travel and managing accounts securely with credentials injected directly to the target system on their behalf. As AI agents increasingly act on behalf of people, the new security question isn?t whether an agent can complete a task, but which identity it uses, what it can access, and whether the user can prove what happened. Sharing credentials directly with the agent exposes them to the model, its memory, and the systems behind it. Requiring a human-in-the-middle to authenticate at each step limits agent productivity, forcing workflows to start, stop, and wait for manual intervention. 1Password for Claude is built for that shift. Trusted Credential Access Framework for AI Agents. Until now, giving an AI agent access to credentials in a browser meant passing them as plain text into the agent's context, where they were directly accessible to the model. 1Password built a zero-exposure security framework that allows agents to use stored credentials in the 1Password vault without them ever reaching the model. Rather than forcing users to choose between sharing their credentials or manually authenticating, it gives agents exactly what they need, scoped to the task, with multiple layers of protection that ensure secrets remain encrypted until the moment they are injected into the page by 1Password. Access is granted per session and scoped to a specific set of approved items. That authorization does not carry over to other sessions, eliminating standing access. 1Password for Claude is the first integration built on it. Key capabilities include: Per-task, user-approved access: Claude requests the credentials required for each task from 1Password, and users approve or deny access with a single biometric prompt, eliminating standing access or persistent sessions. Credentials stay outside the model: Credentials are injected through a secure channel managed by 1Password, outside the agent's view. The password and the MFA one-time code are never accessible to the model, its context, or Anthropic's systems. Agentic Mode: 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. Authenticated multi-site sessions: 1Password brokers credential access across multiple sites within a single task, so Claude can complete multi-step workflows without prompting the user for credentials at each step. Continuous field analysis: 1Password scans the page after every autofill to ensure no secrets remain exposed. If a form submission fails, it wipes any filled values before returning control to the agent. Automatic Vault Lockdown with Agentic Mode. Alongside the Claude integration, 1Password is introducing Agentic Mode for all 1Password users. When a compatible AI agent takes control of the browser, 1Password locks down. The only credentials the agent can reach are those the user has explicitly granted for the current task. Nothing else in the vault is accessible through the browser. Agentic Mode activates automatically and runs quietly in the background. Users can see when it is active directly in the 1Password browser extension, with the option to cancel it at any time. Starting with Claude, the underlying framework is designed to extend to any browser-based agent or platform as the ecosystem grows. For 1Password, this represents a natural expansion from managing people's credentials to governing AI agent access on their behalf. 1Password for Claude is now available to 1Password users on Mac, across business, family, and individual plans. Getting started requires the 1Password desktop app and browser extensions, as well as the Claude desktop app and browser extensions. Future support for payment cards and identity details will be available after launch.