Support & FAQ

Version 1.5.0 added protection for four new sites: Grok, DeepSeek, Kimi, and Perplexity. Chrome requires you to approve access to any new site, so it temporarily disables the extension and shows a permission prompt.

Chrome's prompt says the extension can 'read and change your data on a number of websites' without naming them. Here is the complete list: ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi, and Perplexity. PiiBlocker cannot read any other site.

Click 'Enable' in Chrome's prompt and protection resumes immediately. Nothing about your settings or data changes.

If you use PiiBlocker through your company's IT department, you will not see this prompt. Managed installations update automatically with no interruption.

In free mode, no. All detection and masking happens locally in your browser and the extension makes zero network calls. You can verify this yourself in DevTools. Enterprise deployments report masking events to an admin dashboard, and those reports contain only metadata, never the detected text.

The mapping between placeholders and real data is encrypted (AES-256-GCM) and stored locally. It auto-expires after 4 hours.

Yes. The AI responds using placeholders (like [PERSON_A]), and PiiBlocker automatically swaps them back to your real data. You see the full, natural response.

Seven platforms: ChatGPT, Claude, Gemini, Grok, DeepSeek, Kimi, and Perplexity. All seven are fully supported in the free tier.

The free tier is free forever with full detection and masking. Pro adds convenience features like automatic soft-PII masking and smart strategies. Pro is optional.

Right-click any text and select 'Mask with PiiBlocker' to manually mask anything. Check 'Always detect this' to teach it for future prompts.

Absolutely. PiiBlocker is ideal for professionals who use AI with client data, financial information, or proprietary details.

Yes. PiiBlocker Enterprise is $6.99 per seat/month billed annually, $8.99 per seat/month billed monthly, or $4.99 per seat/month at 100 or more seats billed annually. All three are fixed prices with a checkout in the pricing section. Enterprise adds managed deployment via GPO or MDM, an admin dashboard with seat management, and centralized detection policy. Admin reporting contains only metadata, never the text that was detected. Questions? Contact [email protected].

Make sure the extension is enabled (check the toggle in the popup). If specific data isn't detected, right-click the text and select 'Mask with PiiBlocker' to manually mask it. Check 'Always detect this' to teach the extension for future use.

This means unmasking didn't activate. Try refreshing the page. If the issue persists, the mapping may have expired (4-hour limit). Re-send your prompt with masking enabled.

Currently PiiBlocker is only available as a Chrome desktop extension. Mobile support is on our roadmap.

Not yet. Export/import is planned for a future update.

A list of words and phrases PiiBlocker will leave alone, even if a detector would normally flag them. Use it for things that look like personal data but aren't: your organisation's name, a ward or department, a software product, a drug brand.

Entries match the whole term exactly. Adding "Raman Ward" does not stop "Raman" on its own from being masked.

Be careful with single names. If you allowlist "Raman" because it's a ward, a patient called Raman will also pass through unmasked.

A list of terms PiiBlocker will always treat as personal data. Use it for things the built-in detectors miss: an uncommon surname, an internal patient reference format, a project codename that shouldn't reach an AI service.

The quickest way to add one is to select the text, right-click, choose "Mask with PiiBlocker" and tick "Always detect this".

Dictionary entries only live in your browser. They are never sent anywhere.

The list of data categories PiiBlocker checks for: names, emails, phone numbers, addresses, card numbers, national IDs and so on. Each one can be switched off if it's causing more noise than protection for the way you work.

Turning a category off means that type of data goes through unmasked. If names are giving you false alarms, try the Allowlist first; it keeps name detection on for everyone else.

On an organisation-managed plan, these settings are controlled by your administrator.