Privacy Protection for AI Chatbots
Automatically detect and anonymize personal information before sending messages to ChatGPT and Perplexity AI. Same powerful API as our Desktop App - now in your browser.
Get the Chrome Extension
v1.1.37 · Developer Preview
Download the extension ZIP and install it as an unpacked extension in Chrome. No Chrome Web Store required — free to use.
Download for ChromeInstallation Instructions
- 1Download the ZIP file and extract it to a folder
- 2Open Chrome and navigate to chrome://extensions
- 3Enable "Developer mode" using the toggle in the top-right corner
- 4Click "Load unpacked" and select the extracted folder
- 5The extension is now installed! Click the extension icon and sign in with your anonym.legal account
Chrome Web Store approval is in progress. Once published, the extension will be available for automatic installation.
Supported AI Platforms
The extension works with major AI chat platforms and can be extended to any website
ChatGPT
chatgpt.com
Perplexity
perplexity.ai
Claude
claude.ai
Gemini
gemini.google.com
DeepSeek
chat.deepseek.com
Abacus.ai
chatllm.abacus.ai
Custom connectors can be developed for any website. Contact us for enterprise integration with your internal AI tools.
Core Features
Same powerful features as our Desktop App - powered by the same API
Real-Time Interception
Automatically intercepts messages before they're sent to AI. No manual copy-paste required.
- Intercepts on Send button click
- Works with Enter key submission
- No workflow disruption
- Instant PII detection
Hybrid Detection Engine
Detects 285+ entity types across 48 languages using deterministic regex + NLP patterns with configurable confidence thresholds.
- 285+ entity types
- 48 language support
- Context-aware recognition
- Adjustable sensitivity
Preview Before Send
Review detected PII in a preview modal before sending. Toggle entities, change methods, select presets.
- Entity-by-entity control
- Method selection per message
- Preset quick-switch
- Encryption key selector
Response De-anonymization
Encrypted values in AI responses are automatically decrypted and displayed with visual highlighting.
- Auto-decrypt responses
- Visual highlighting
- Toggle original/encrypted
- Copy decrypted values
5 Anonymization Methods
Choose the right method for each message: Encrypt (reversible), Replace, Mask, Redact, or Hash.
- Encrypt with personal keys
- Replace with fake data
- Mask partially
- Redact completely
Compliance Presets
Pre-configured detection profiles synced from your account. GDPR, HIPAA, PCI-DSS, and country-specific presets.
- 85+ country presets
- GDPR/HIPAA ready
- Custom presets
- Searchable selector
File Anonymization
Anonymize text files before uploading to AI chats. Supports .txt, .md, .csv, .json, .xml, and more.
- Drag-and-drop files
- Preview before upload
- De-anonymize in responses
- Up to 50KB files
48 Languages
Full PII detection support for 48 languages including RTL languages (Arabic, Hebrew, Persian, Urdu).
- Auto language detection
- Multi-language messages
- RTL support
- Regional entity formats
5 Anonymization Methods
Same methods as Desktop App and Office Add-in - choose based on your compliance requirements
Encrypt
Reversible with key
Replace
Fake data
Mask
Partial hide
Redact
Complete removal
Hash
SHA-256
Intelligent De-anonymization
When AI responds with encrypted values, the extension automatically decrypts and highlights them
Auto-Decrypt
Both user messages and AI responses automatically decrypted
Visual Highlight
Green gradient with entity badges for easy identification
Toggle View
Switch between original and encrypted values instantly
Copy Buttons
Copy individual values or entire decrypted messages
Rich Tooltips
Hover to see entity type, key name, and encrypted value
Zero-Knowledge Security
Your password never leaves your device - same security as Desktop App
Enterprise Deployment
Deploy the extension organization-wide with enforced policies, managed presets, and centralized encryption keys
Admin Enforcement
IT administrators can enforce protection policies, preventing users from disabling anonymization on approved sites.
Managed Presets
Deploy organization-specific presets that define which entities to detect and how to anonymize them.
Encryption Policies
Enforce encryption method with organization-managed keys. Ensure all AI interactions use reversible anonymization.
Custom Entities
Define custom entity patterns for internal identifiers, project codes, or proprietary data formats.
Audit Logging
Track anonymization events for compliance reporting. Integration with SIEM systems available.
Bulk Deployment
Deploy via Group Policy, MDM, or enterprise browser management. Pre-configured with organization settings.
Custom Extension Packaging
We can package the extension with your organization's branding, pre-configured settings, and locked-down policies.
- Custom branding and icons
- Pre-configured API credentials
- Enforced site restrictions
- Locked anonymization methods
- Mandatory encryption keys
- Disabled user overrides
- Silent installation support
- Automatic updates from your server
Current & Planned Features
The extension is actively developed with new features planned based on user feedback
Currently Available (v1.0.141)
- Text message anonymization
- File anonymization (.txt, .md, .csv, .json, .xml, .yaml)
- 5 anonymization methods
- Real-time response decryption
- 85+ country presets
- 48 language support
- Encryption key management
- Toggle original/encrypted view
Planned (Roadmap)
- All file formats (PDF, DOCX, XLSX) like Desktop App
- Batch file processing
- Image anonymization
- Chrome Web Store publication
- Firefox and Edge extensions
- More AI platform connectors
- Offline mode with local cache
- Advanced analytics dashboard
Powered by the Same API
The Chrome Extension uses exactly the same API as our other products. If you're already using anonym.legal, the extension works with your existing presets, encryption keys, and settings.
Plan Availability
The Chrome Extension is available on all paid plans
Free plan users can upgrade to access the Chrome Extension. Enterprise plans include custom deployment support.
Data Loss Prevention Built for Browser-Based AI
Traditional enterprise DLP was designed for file transfers and email — not for the new reality where employees type sensitive data directly into ChatGPT, Claude, and Gemini. anonym.legal's Chrome Extension delivers DLP where the data actually leaks: inside the browser, before the prompt reaches the AI provider.
of employees paste sensitive data into AI tools (LayerX 2025)
of data exfiltration now happens via AI tools
to deploy vs weeks for enterprise DLP
Frequently Asked Questions — Browser DLP for AI
How do I stop my team from accidentally pasting customer data into ChatGPT?
anonym.legal's Chrome Extension intercepts clipboard content before it reaches AI chatbots (ChatGPT, Claude, Gemini, DeepSeek, Perplexity), automatically detecting and replacing PII with anonymized tokens. PII detection uses anonym.legal's EU-hosted API — no data is sent to the AI provider until it's been sanitized. The extension works transparently, requiring no workflow changes from your team.
Malicious Chrome extensions stole 900,000 ChatGPT conversations — how do I know a privacy extension is safe?
anonym.legal's Chrome Extension uses Manifest V3 (the latest Chrome security standard) with minimal permissions — it only activates on AI chatbot sites you explicitly enable. PII detection uses anonym.legal's EU-hosted API with zero-knowledge design: text is analyzed in memory and not stored. The extension's optional_host_permissions model means it cannot access any site you haven't explicitly authorized.
Can I use ChatGPT for customer support tasks without violating GDPR?
anonym.legal's Chrome Extension anonymizes customer PII before it reaches ChatGPT, transforming real names, addresses, and identifiers into anonymized tokens. Since only sanitized text reaches OpenAI's servers, no personal data is processed by the AI provider — eliminating the GDPR data transfer concern. The reversible encryption feature (on paid plans) allows restoring original names in ChatGPT's response for the final customer communication.
How do I prevent employees from accidentally sending customer PII to ChatGPT in support responses?
The Chrome Extension automatically detects PII in text being submitted to AI chatbots and replaces it with anonymized tokens before submission. This happens transparently — employees type or paste normally, and the extension intercepts the content at the browser level. Supports ChatGPT, Claude, Gemini, DeepSeek, and Perplexity with per-site activation controls.
How do I verify a Chrome privacy extension isn't itself collecting my data?
anonym.legal's Chrome Extension uses Manifest V3 with optional_host_permissions — it cannot access any website unless you explicitly grant permission via the extension popup. PII detection occurs via anonym.legal's EU-hosted API with zero-knowledge architecture: text is analyzed in transit and never stored. The extension requests no background data collection permissions and activates only on AI chatbot sites you've enabled.
Developers paste environment variables and secrets into Claude for debugging — how do we catch this at the browser level?
The Chrome Extension detects API keys, JWT tokens, database connection strings, and environment variables in text being submitted to AI chatbots, replacing them with safe placeholders before transmission. For Claude specifically, the MCP Server provides deeper integration at the AI tool level. Together, they create a two-layer defense against accidental secret exposure in developer workflows.
We need to share clinical cases with an AI for learning — but patient names and DOBs can't be included. How?
The Chrome Extension automatically detects patient names, dates of birth, MRNs, and other PHI before text reaches the AI chatbot. Clinicians paste the case study normally — the extension intercepts and anonymizes all PHI in real time, sending only de-identified text to the AI. This enables AI-assisted clinical learning while maintaining HIPAA de-identification requirements.
From the Blog
View all articlesAI Coding Assistants Leak Production PII
Unit test fixtures with real customer records. Log files with production data for debugging. GitHub found 39 million secrets leaked in 2024.
Internal Wiki PII: Confluence Customer Data
Support teams document processes with screenshots of customer accounts. Over 3 years, that's thousands of GDPR data minimization violations in your.
Screenshot PII: Leaks in Internal Tools
Slack, Teams, Jira, and email regularly receive screenshots containing customer PII. This access-control violation bypasses every DLP tool.
Interested in the Chrome Extension?
Contact us to request testing access or discuss enterprise deployment options. We'll help you evaluate the extension for your organization's AI privacy needs.