Shield: AI Privacy for ChatGPT & Claude 作者: Infinium

🛡️ InfiniUm Shield — AI Privacy Firewall

Every message you send to ChatGPT, Claude, or Gemini passes through their servers. Shield intercepts your prompts before they leave your browser, replaces sensitive data with safe tokens, and swaps them back in the AI's response.

Works automatically. Zero configuration. No account required.



What Shield protects:

🔴 Critical — API keys, passwords, database connections, JWT tokens, private keys, secret environment variables

🟡 Warning — Email addresses, phone numbers, credit cards, private IP addresses, SSNs

🟢 Info — Internal hostnames, system paths, URLs with credentials, personal names



How it works:
1. You type a message in ChatGPT, Claude, or Gemini
2. You press Send — Shield intercepts in milliseconds
3. Sensitive values replaced: [EMAIL_1] [API_KEY_1] [PASSWORD_1]
4. Clean prompt sent to AI — your data never exposed
5. AI responds — tokens swapped back to real values automatically



Free tier — 100% local, forever:
- All processing happens inside your browser
- Zero data sent anywhere — ever
- No account, no registration, no telemetry

Pro tier — $8/mo via infinium.tools:
- Custom rules — protect project names, client names, internal codenames
- Sync rules across all browsers and devices
- Advanced detection — .env files, cloud credentials, Stripe keys
- Full audit log (metadata only, never content)



GDPR & Compliance — Personal data is masked before transmission, helping organisations meet data minimisation obligations under GDPR, HIPAA, and SOC 2.

Built by InfiniUm Tools — infinium.tools/shield