By George Curta · Last updated 2026-04-07
Troubleshooting & FAQ
Solutions to common issues and answers to frequently asked questions about the Chrome Extension.
Common Issues
Extension does not activate on an AI site
The most common issue. The extension uses optional host permissions that must be enabled per-site.
Click the anonym.legal extension icon in your toolbar.
Find the AI site in the list and enable the toggle switch.
Accept the Chrome permission prompt when it appears.
Refresh the AI site page after enabling the permission.
Chat input not detected
The extension needs its bridge to connect with the site's editor component.
Refresh the page and wait a few seconds for the bridge to initialize.
Some AI sites use ProseMirror rich-text editors that require the bridge pattern for MAIN/ISOLATED world communication.
If the problem persists, try disabling and re-enabling the site in the extension popup.
Text is not being anonymized
Multiple factors can prevent anonymization from activating.
Open the extension popup and verify you are signed in to your anonym.legal account.
Confirm the current site is enabled in the extension popup.
Check that your account has sufficient credits remaining.
Try refreshing the page to re-establish the connection.
Claude /new page first message
A known complexity with Claude's SPA navigation pattern.
When you send a message on Claude's /new page, Claude navigates to a /chat/xxx URL. This SPA transition destroys and recreates the extension connector. The extension preserves the anonymization cache across this transition, but timing can vary.
Workaround: If de-anonymization does not work on the first message, refresh the page. Subsequent messages in the same chat will work normally.
De-anonymized text not appearing
Response de-anonymization depends on the connector being active.
Refresh the page to re-establish the connector.
The extension caches anonymization mappings across page navigations, so refreshing should restore de-anonymization.
If the issue persists, check the browser developer console (F12) for error messages and contact support.
File upload not supported on a site
Not all AI platforms support direct file upload interception.
When direct file upload anonymization is not available on a particular site, the extension provides a clear fallback message with a "Copy anonymized text" button.
Workaround: Click the fallback button to copy the anonymized file content, then paste it into the chat input manually. Supported file types: .txt, .md, .csv, .json, .xml, .yaml, .log (max 50KB).
Frequently Asked Questions
Host permissions are not working - the extension does not activate on an AI site
Open the extension popup by clicking the anonym.legal icon in your toolbar. Check that the specific AI site is enabled (toggle switch is on). After enabling, you must refresh the AI site page for the extension to activate. Each browser profile requires its own permission grants -- permissions do not carry over between profiles.
The extension is not detecting text in the chat input field
Some AI platforms use ProseMirror or custom rich-text editors that require the extension's bridge to establish a connection. Refresh the page and wait a few seconds for the bridge to initialize. If the issue persists, check that the site is enabled in the extension popup and that you are signed in to your anonym.legal account.
Text is not being anonymized when I type or paste into the chat
Verify three things: (1) Click the extension icon and confirm you are signed in to your anonym.legal account. (2) Check that the current AI site is enabled in the extension popup. (3) Make sure you have sufficient units in your account. If all three are correct, try refreshing the page.
First message on Claude's /new page does not work correctly
Claude uses SPA (Single Page Application) navigation. When you send your first message on the /new page, Claude navigates to a /chat/xxx URL. The extension handles this transition by preserving the anonymization cache across page navigations. If de-anonymization does not work on the first message, refresh the page -- subsequent messages will work normally.
De-anonymized text is not appearing in the AI response
SPA navigation on some AI platforms may reset the connector. Try refreshing the page. The extension preserves the decryption cache across page transitions, but in some cases the connector needs to re-establish after navigation. If the issue persists after a refresh, check the browser console for error messages and contact support.
File upload anonymization is not available on a specific AI site
Not all AI platforms support direct file upload interception. When direct upload is not possible, the extension provides a 'Copy anonymized text' fallback. Click the fallback button, then paste the anonymized content manually into the chat input. Supported file types: .txt, .md, .csv, .json, .xml, .yaml, .log (maximum 50KB).
Still Need Help?
If you could not find a solution above, please reach out to our support team. Include the following information to help us resolve your issue faster:
- Browser name and version (e.g., Chrome 122, Edge 122)
- Extension version (visible in the extension popup)
- Which AI site is affected
- Steps to reproduce the issue
- Any error messages from the browser console (F12)
About this page
We update this page when our platform or the law changes.
Read our founder note for how we work.
Each change shows up in the timestamp at the top.
Related reading
- Common questions
- Glossary
- How tokens work
- Security posture
- Where we comply
- What we detect
- Case studies
- Release notes
We follow these rules
- GDPR (EU 2016/679).
- ISO/IEC 27001:2022.
- NIS2 (EU 2022/2555).
- HIPAA safe harbor under 45 CFR § 164.514(b)(2).
Our promise
We do not sell your data.
We do not train models on your text.
We store your files in Germany.
You can delete your account at any time.
You own your work.
Where we run
Our servers live in Falkenstein, Germany.
We use Hetzner. They hold ISO 27001 certification.
All data stays in the EU.
Backups run every day.
Need help?
Email support@anonym.legal.
We reply within one business day.
How we test
We run a full check suite on every release.
Each surface gets its own sweep script and report.
Human reviewers spot-check the output each week.
We track recall and precision on a labelled set.
Bad runs block the deploy.
What we never do
- We never sell your information to third parties.
- We never train models on what you upload.
- We never keep your work after you delete it.
- We never share keys with any outside firm.
- We never run ads inside the product.
Plans in plain words
We sell credits, not seats.
One credit covers one short job.
Long jobs use a few credits each.
You can top up at any time.
Unused credits roll over each month.
Read the plans page for current rates.
Who built this
A small team of engineers and lawyers built this.
We ship from Europe and work in the open.
Our founder note spells out why we started.
Where to start
- Open the web app and try a sample file.
- Learn how credits get counted.
- See current plans and limits.
- Meet the team behind the product.
How the parts fit
A browser add-on cleans text inside Chrome.
A Word plug-in handles drafts in Office.
A small desktop tool works on whole folders.
An agent protocol link feeds large models safely.
All four share one core engine and one rule set.
Words from our team
We started this work after a lunch about cookies.
One friend kept getting odd ads on her phone.
We asked why a court file leaked through a draft.
We sketched the first build on a napkin that week.
By month three we had a tiny demo for a friend.
She used it on her first case the next day.
Common questions we hear
Can the tool read scanned PDFs? Yes, with OCR.
Does it work on long files? Yes, in small chunks.
Can I roll my own rule set? Yes, save it as a preset.
Does it run offline? The desktop build runs offline.
Do you keep my files? No, the cloud build wipes after each run.
Will it learn from my work? No, we never train on inputs.
A short tour of the workflow
Upload a file or paste a snippet of prose.
Pick the entities you want gone from the draft.
Choose a method: replace, mask, hash, encrypt, or redact.
Press run and watch the side panel show each hit.
Skim the result and tweak any rule that misfired.
Save the cleaned file or send it to a teammate.