Item logo image for AI Leak Guard

AI Leak Guard

ExtensionPrivacy & Security
Item media 3 (screenshot) for AI Leak Guard
Item media 1 (screenshot) for AI Leak Guard
Item media 2 (screenshot) for AI Leak Guard
Item media 3 (screenshot) for AI Leak Guard
Item media 1 (screenshot) for AI Leak Guard
Item media 1 (screenshot) for AI Leak Guard
Item media 2 (screenshot) for AI Leak Guard
Item media 3 (screenshot) for AI Leak Guard

Overview

Free local-only protection against accidental AI data leaks. Detects and masks sensitive data before you paste into AI tools.

AI Leak Guard is a privacy layer between healthcare workers and the AI tools they already use every day. When you paste text into ChatGPT, Claude, Gemini, or Copilot, AI Leak Guard checks it first — right in your browser — for the kinds of details that identify a patient: names, dates of birth, addresses, phone numbers, email addresses, medical record and member numbers, and government or financial identifiers. If it finds any, it shows you exactly what it would hide and lets you decide: paste the protected version, paste the original as-is, or cancel. Nothing is sent until you choose. Clinical details on their own — a medication name or a diagnosis code — are treated as context, not as something to hide, so you only see a prompt when there is a real identifier to protect. No noise on ordinary text. How it works - Detection happens entirely on your device. Your text is never uploaded, stored, or sent anywhere. - You see a preview of what will be hidden before anything is inserted, and you make the final call. - It works on the major AI chat tools and stays out of your way the rest of the time. Built to be trustworthy - 100% local. No account, no login, no backend, no analytics. - Free for individual healthcare workers. - Open source, so anyone can read exactly what it does. What AI Leak Guard does - Spots common patient identifiers before you paste them into an AI tool. - Lets you replace those details with placeholders in one click. - Helps your team follow an acceptable-use policy for AI. What AI Leak Guard does not do - It does not make ChatGPT, Claude, Gemini, or Copilot compliant with any regulation. - It does not guarantee that every possible identifier is caught. - It is not a substitute for your organization's privacy and security program, and it is not legal or compliance advice. AI Leak Guard reduces the chance and the impact of accidentally sharing patient information with an AI tool. It is a preventive privacy control that keeps you in control.

Details

  • Version
    1.1.1
  • Updated
    August 18, 2026
  • Offered by
    Zabcore
  • Size
    43.72KiB
  • Languages
    English
  • Developer
    Email
    devcore@zabcore.com
  • Non-trader
    This developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.

Privacy

Manage extensions and learn how they're being used in your organization
The developer has disclosed that it will not collect or use your data. To learn more, see the developer’s privacy policy.

This developer declares that your data is

  • Not being sold to third parties, outside of the approved use cases
  • Not being used or transferred for purposes that are unrelated to the item's core functionality
  • Not being used or transferred to determine creditworthiness or for lending purposes
Google apps