# PiiBlock - PiiBlocker

> 43% of workers paste sensitive data into AI chatbots without realizing the risks (Source: National Cybersecurity Alliance, 2025–2026). PiiBlocker by PiiBlock is a free PII Chrome extension and AI prompt anonymizer that redacts personally identifiable information before it reaches ChatGPT, Claude, and Gemini. It works as a free alternative to enterprise AI DLP and shadow-AI tools such as Lakera. 100% local processing. Zero data collection. No servers.

## Category

PiiBlocker fits into three overlapping product categories: (1) PII Chrome extension / PII masking tool, (2) AI prompt anonymizer / prompt privacy extension, and (3) browser-based AI DLP / shadow-AI control. It is positioned for individuals, healthcare workers, lawyers, and small teams who need to redact sensitive data before sending prompts to AI chatbots, without paying for an enterprise DLP suite.

## The Problem

Every day, people paste names, credit cards, medical records, client files, and API keys into AI chatbots. Once sent, that data is stored on third-party servers, potentially used for model training, and at risk of exposure through data breaches. Enterprise privacy tools exist but cost hundreds per month and require IT teams to deploy.

## What PiiBlocker Does

PiiBlocker solves this by scanning text in real-time as users type into AI chatbot interfaces. When PII is detected, the extension highlights it and presents a confirmation dialog before the message is sent. Critical data types (credit cards, SSNs, API keys, passwords) are auto-masked. Soft PII types (names, addresses, phone numbers) are flagged for user decision. The AI receives placeholder tokens like [PERSON_A] or [CREDIT_CARD_1] instead of real data. When the AI responds, PiiBlocker swaps placeholders back to real values so the user sees their original data seamlessly.

## PII Types Detected

PiiBlocker detects 15+ types of personally identifiable information:

- Credit card numbers (with Luhn validation)
- Social Security numbers
- API keys and secrets (OpenAI, AWS, GitHub, and more)
- Passwords
- Person names
- Physical addresses
- Phone numbers (US and UK formats)
- Email addresses
- Dates of birth
- Ages
- Salary and income figures
- Medical conditions
- Employer names
- Bank account numbers
- UK National Insurance numbers

## Security Architecture

- 100% client-side processing - all detection and masking runs in the browser
- Zero servers - PiiBlock does not operate backend infrastructure
- Zero data collection - no telemetry, no analytics, no cookies, no third-party scripts
- AES-256 encryption for mapping data stored in browser memory
- Encryption keys exist only in memory and are lost when the browser closes
- Encrypted mappings auto-expire after 4 hours
- One-click purge to wipe all stored data instantly

## Release History

Current version: v1.1.7 (May 16, 2026). PiiBlocker follows semantic versioning. Full release notes at https://www.piiblock.com/changelog.

- v1.1.7 (May 16, 2026) - Major update. Added enterprise managed-policy support (GPO/MDM/Google Admin Console toggle-lock for IT admins), Medical Record Number (MRN) detection for healthcare workers, dark mode across the popup and weekly report, site indicator strip, and privacy score qualifier text. Improved popup layout (compact no-scroll), Personal Dictionary (search, sort, two-stage delete). Fixed a critical ChatGPT race condition that could occasionally submit unmasked text, plus zombie-tab service worker recovery and tooltip clipping.
- v1.1.5 (April 12, 2026) - Added UK National Insurance Number and UK mobile phone number detection. Fixed Claude submit-button race condition that required 2-3 clicks. Improved person-name detection accuracy.
- v1.1.1 (March 16, 2026) - Hotfix for extension context invalidation. Added a fail-safe that blocks submit if detection is in a broken state, preventing accidental PII leaks.
- v1.1.0 (March 12, 2026) - Renamed product from PrivacyShield to PiiBlocker across all user-facing surfaces.
- v1.0.1 (March 5, 2026) - Initial public release on the Chrome Web Store. 17 PII types across critical/soft/custom tiers, ChatGPT/Claude/Gemini support, AES-256-GCM encrypted mappings, 4-hour auto-expiry, personal dictionary, weekly privacy report.

## Supported Platforms

- ChatGPT (chat.openai.com)
- Claude (claude.ai)
- Google Gemini (gemini.google.com)

## Pricing

- Free tier: All core PII detection and masking features, unlimited usage, no account required
- Pro tier (coming soon, $4.99/month): Fully automatic soft-PII masking, smart masking strategies, privacy dashboard, additional platform support, per-site rules

## Links

- Homepage: https://www.piiblock.com/
- Features: https://www.piiblock.com/features
- Use Cases: https://www.piiblock.com/use-cases
- Chrome Web Store: https://chromewebstore.google.com/detail/privacyshield/nklghhkmhkmckonncilnaohlihfacoee
- Support: https://www.piiblock.com/support
- Privacy Policy: https://www.piiblock.com/privacy
- Terms of Service: https://www.piiblock.com/terms
- Changelog: https://www.piiblock.com/changelog
- GitHub: https://github.com/piiblocker-coder/privacyshield
- X/Twitter: https://x.com/PIIBlocker
- Demo Video: https://www.youtube.com/watch?v=VpYqkC-_UVg
- LinkedIn: https://www.linkedin.com/company/piiblock
- Blog - How PiiBlocker Works: https://www.piiblock.com/blog/how-piiblocker-works-technical-deep-dive
- Blog - 5 Times Sensitive Data Was Leaked Through AI Chatbots: https://www.piiblock.com/blog/5-times-sensitive-data-leaked-ai-chatbots
- Blog - DLP vs. Browser Extensions - Blocking PII in AI Chatbots: https://www.piiblock.com/blog/dlp-vs-browser-extensions-pii-ai-chatbots
- Blog - What Healthcare Staff Paste into ChatGPT (And Why IT Can't See It): https://www.piiblock.com/blog/healthcare-staff-paste-chatgpt-pii
- Blog - AI Governance for Small Medical Practices (5 Numbers Define the Gap): https://www.piiblock.com/blog/ai-governance-small-medical-practices-gap