Shield: AI Privacy for ChatGPT & Claude

🛡️ INFINIUM SHIELD — AI PRIVACY FIREWALL Every message you send to ChatGPT, Claude, or Gemini passes through their servers — and stays there. Shield intercepts your prompts before they leave your browser, replaces sensitive data with safe tokens, and swaps them back in the AI's response. You get the same answer. The AI never sees your real data. Works automatically. Zero configuration. No account required. ───────────────────────────────────── WHAT SHIELD PROTECTS ───────────────────────────────────── Shield automatically detects and masks 19 categories of sensitive data: 🔴 CRITICAL • API keys — AWS, OpenAI, Anthropic, GitHub, Slack and generic api:/token:/bearer: patterns • Passwords — all common password field formats • Database connection strings — PostgreSQL, MySQL, MongoDB, Redis and more • JWT tokens • Private keys — RSA, EC, OpenSSH, PGP • Secret environment variables 🟡 WARNING • Email addresses • Phone numbers • Credit card numbers • Private IP addresses (RFC 1918) • Social Security Numbers (SSN) 🟢 INFO • URLs containing embedded credentials • Internal hostnames (*.internal, *.corp, *.local) • System file paths • Personal names ───────────────────────────────────── HOW IT WORKS ───────────────────────────────────── 1. You type a message in ChatGPT, Claude, or Gemini 2. You press Enter or click Send 3. Shield intercepts the prompt in milliseconds 4. Sensitive values are replaced with tokens: [EMAIL_1], [API_KEY_1], [PASSWORD_1] 5. The clean prompt is sent to the AI 6. When the AI responds, tokens are swapped back to real values 7. You read natural, accurate text — your data was never exposed The entire process is invisible. You work exactly as you normally would. ───────────────────────────────────── PRIVACY GUARANTEE ───────────────────────────────────── Shield is built on a single principle: your data never leaves your device without your knowledge. FREE TIER — 100% LOCAL • All processing happens inside your browser • Zero data sent to any server — ever • No account required, no registration, no email • No analytics, no telemetry, no tracking • Works fully offline PRO TIER — METADATA ONLY • Your actual prompt content is still never transmitted • The audit log records only: which AI tool, how many items were masked, what categories • Real values are never logged, never sent, never stored on our servers • Custom rules are synced as plain text terms — no prompt content, ever ───────────────────────────────────── GDPR & COMPLIANCE ───────────────────────────────────── For organisations under GDPR, HIPAA, SOC 2, or ISO 27001, sharing personal data with AI providers without safeguards creates significant compliance risk. Shield ensures personal data is masked before transmission, enforcing data minimisation by architecture, not policy. GDPR — Masks personal data before it reaches third-party AI processors. HIPAA — Reduces PHI exposure for healthcare organisations using AI tools. SOC 2 — Provides a measurable technical control for AI data confidentiality risks. ISO 27001 — Auditable control for the emerging AI tool risk category. Note: Shield is a technical control, not a compliance certification. Always consult your legal and compliance teams. ───────────────────────────────────── SUPPORTED AI PLATFORMS ───────────────────────────────────── ✅ ChatGPT (chatgpt.com + chat.openai.com) ✅ Claude (claude.ai) ✅ Gemini (gemini.google.com) ───────────────────────────────────── FREE vs PRO ───────────────────────────────────── FREE — Forever, no account needed ✓ All 19 built-in detection rules ✓ Automatic interception on ChatGPT, Claude & Gemini ✓ Token swap in AI responses ✓ Popup showing what was masked ✓ Per-site and global on/off toggle ✓ 100% local — nothing sent anywhere PRO — $8/month via infinium.tools ✓ Everything in Free ✓ Custom rules — protect project names, client names, internal codenames ✓ Sync custom rules across all your browsers and devices ✓ Advanced detection — .env files, cloud credentials, Stripe keys, code secrets ✓ Full audit log — what was masked, when, on which AI tool ✓ Priority support ───────────────────────────────────── A REAL EXAMPLE ───────────────────────────────────── Without Shield, pasting this into ChatGPT: "DB: postgres://admin:S3cr3tPass@db.internal:5432/prod Token: eyJhbGciOiJIUzI1NiJ9.eyJ1c2VyIjoiam9obn0.abc123 Contact: john.smith@acme-corp.com" ...sends your database password, JWT token and email directly to OpenAI's servers. With Shield, the same message becomes: "DB: [DB_CONN_1] Token: [JWT_1] Contact: [EMAIL_1]" The AI gives exactly the same help. Your data never left your browser. ───────────────────────────────────── PERFECT FOR ───────────────────────────────────── 👨‍💻 Developers — Stop sharing API keys and DB passwords when asking AI for code help 🏢 Companies — Protect client names, project codenames and internal data ⚖️ Legal Teams — Reduce GDPR exposure when staff use AI for document review 🏥 Healthcare — Prevent inadvertent sharing of patient-related information 🔐 Security Teams — Enforce data hygiene across AI tool usage ───────────────────────────────────── WHAT SHIELD DOES NOT DO ───────────────────────────────────── ✗ Does not encrypt prompts — it masks them ✗ Does not protect file uploads or attachments ✗ Does not work on AI tools outside the supported platforms ✗ Does not guarantee 100% detection — novel formats may be missed ✗ Is not a substitute for a full data protection programme ───────────────────────────────────── PERMISSIONS EXPLAINED ───────────────────────────────────── • storage — Save settings and statistics locally • tabs — Detect which AI site is open for popup display • alarms — Pro only: daily rule sync in background Shield does NOT access browsing history, bookmarks, clipboard, or any data unrelated to supported AI sites. ───────────────────────────────────── ENTERPRISE DEPLOYMENT ───────────────────────────────────── IT administrators can force-install Shield on managed Chrome profil…