


Overview
Warns, redacts, or blocks sensitive data before it is sent to public AI tools.
PromptFence is a local-first privacy gateway that prevents sensitive data, credentials, and customer PII from leaking into public AI tools. The extension runs entirely in your browser to inspect prompts and file uploads before submission. When sensitive patterns are detected, PromptFence can warn you, replace matched values with consistent reversible placeholders, or block credentials entirely according to your selected policy. KEY FEATURES • Reversible Masking & Auto-Unmasking: Replaces sensitive data with structured tokens (such as [EMAIL_1] or [PHONE_1]) before transmission, then automatically rehydrates the original values in your view when the AI responds. Your workflow stays natural, while the AI model never sees your private information. • In-Memory File Upload Sanitization: Intercepts plaintext and data attachments and scrubs matched values in RAM before the file can be uploaded to the AI chat. • Comprehensive Pattern Detection: Identifies API keys, passwords, database connection strings, auth tokens, private keys, healthcare identifiers (HIPAA), financial accounts, and personal identifiers (PII). • Hard-Blocked Credentials: Automatically stops high-entropy secrets and authentication keys from being submitted under all policy presets (Light, Balanced, or Strict). • Multi-Model Protection: Works natively inside ChatGPT, Claude, Gemini, and Perplexity web interfaces. • Quiet Drafting Workflow: Clean, non-intrusive notifications and a compact badge that stay out of your way until high-risk data is detected. • 100% Local Privacy by Default: Operates completely offline on your device with zero account, zero login wall, and zero network calls required for personal use. • Enterprise Fleet & MSP Ready: Optionally connects to the PromptFence dashboard for centralized team policies, verifiable audit logs, and zero-touch deployment (Microsoft Intune, Windows GPO, macOS .plist) with tamper protection. • Developer Ecosystem: Includes companion guardrails for terminal workflows, Cursor, Claude Code, and git pre-commit hooks via the open-source CLI. PRIVACY & SECURITY ARCHITECTURE Prompt scanning, token replacement, and policy decisions run locally on your device. PromptFence never stores, transmits, or logs raw prompt text. When connected to an optional organization dashboard, only high-level finding categories, action metadata, an irreversible SHA-256 content hash, the AI domain, and a truncated redacted sample are synced for compliance auditing. Pattern-based detection is designed to support your data governance. Users should always review flagged prompts before submission. PromptFence is engineered by TensorJetAI for individuals, engineering teams, and regulated organizations using modern AI.
5 out of 51 rating
Details
- Version1.0.0
- UpdatedNovember 15, 2026
- Size67.31KiB
- LanguagesEnglish
- DeveloperWebsite
Email
security@tensorjetai.com - Non-traderThis developer has not identified itself as a trader. For consumers in the European Union, please note that consumer rights do not apply to contracts between you and this developer.
Privacy
This developer declares that your data is
- Not being sold to third parties, outside of the approved use cases
- Not being used or transferred for purposes that are unrelated to the item's core functionality
- Not being used or transferred to determine creditworthiness or for lending purposes
Support
For help with questions, suggestions, or problems, visit the developer's support site