Privacy Policy
Last updated: July 4, 2026 · Extension version: 0.2.0
What data is detected
The extension scans the text you type and the PDF files you upload on claude.ai and chatgpt.com, looking for the following categories of personal data:
- People's names
- French social security numbers (national ID)
- IBAN and bank card numbers
- Email addresses
- Phone numbers
- SIRET (company registration) numbers
- IP addresses
Each detected data point is replaced with an anonymous token (for example {{PERSON_a1b2}}) before sending. The model's reply is then re-displayed with the original values restored locally, in your browser only.
Where processing happens
| Component | Where it runs | Data that passes through |
|---|---|---|
| Regular-expression detection | In the browser (extension) | Prompt text, before sending |
| Advanced detection (NER model) and PDF redaction | Local ndaact.ai application on your machine (127.0.0.1) |
Prompt text / PDF content, never sent outside your machine |
| Detection history (audit) | Local chrome.storage, on your machine |
Personal data type, token, timestamp — never the original value |
What is never sent to ndaact.ai
No personal data detected by the extension is sent to a server operated by ndaact.ai or Inkan.link. The extension only communicates with two destinations: the LLM site you use (claude.ai/chatgpt.com, which only ever receives substitution tokens — without the mapping table or the session salt, so with no reasonable means of re-identifying anyone) and the local ndaact.ai application on 127.0.0.1, which runs entirely on your own computer.
Terminology. This processing is client-side pseudonymisation (GDPR Art. 4(5)): reversible for you, since the mapping table stays on your machine. We therefore don't call it "anonymisation" on your side. For the LLM provider and any third party, however, it aims for the effect of de-identification: the tokens are opaque to them, with no reasonable means of re-identification (the relative approach taken by the Court of Justice of the EU, Case C-413/23 P, 4 September 2025). Only the detected entities are redacted; we don't claim to anonymise the entire prompt.
Sharing with third parties
ndaact.ai does not sell, rent, or share any personal data with a third party. No data is used for advertising or behavioural analytics purposes. The only statistics collected are anonymous and concern usage of this website (Matomo, self-hosted), not the extension itself.
Browser permissions
The extension requests a minimal set of Chrome permissions, each strictly necessary for detecting and redacting personal data before sending: network access on claude.ai/chatgpt.com/127.0.0.1, reading the active tab, script injection, local storage, periodic alarms, and notifications. The detail of each permission and its justification are documented on the Chrome Web Store listing and available on request.
Your rights
Because processing is entirely local, you keep full control: you can disable protection at any time from the extension popup, review the full detection history, and uninstall the extension to immediately delete all data stored locally (chrome.storage).
Contact
For any question about this privacy policy: contact@ndaact.ai.