U
UtilyxHub
AI Guardrail ← All Tools
🤖 100% In-RAM AI Guardrail • Zero Data Retention • Token Anonymization

AI Prompt PII & Secret Scanner

Prevent confidential data leaks to ChatGPT, Claude, or Gemini. Detect and pseudonymize API keys, payment cards, SSNs, and personal emails before you submit prompts.

Input Raw AI Prompt or Code
| |
AI Prompt Security Rating
Clean Prompt (Safe for AI)
0 Leaks Detected

No API credentials, payment cards, national IDs, or personal contact identifiers were detected. This prompt is safe for public LLM models.

API & Secret Keys None
Payment & Financials None
PII & Contact Data None
Identity Tokens / SSN None
Anonymized Prompt (Safe to Submit)
Enter prompt above and click Scan & Scrub Prompt to view anonymized version.

Submit this anonymized version to ChatGPT or Claude. The model understands the context through the synthetic tokens without exposing real identities.

Substitution Map In-RAM Only

Use this key to map placeholders back to original secrets once the AI responds:

No active substitutions.
Zero-Retention Security

This substitution dictionary exists only in active browser memory and is purged when you close this window.

Supported PII & Secret Detection Taxonomy

Confidential entities monitored by our client-side heuristic redaction engine.

Entity Category Pattern & Structure Monitored Synthetic Substitution Token
API & Cloud Keys OpenAI (sk-...), AWS (AKIA...), GitHub (ghp_...), Bearer Tokens <API_KEY_n>
Payment Cards Visa, MasterCard, Amex, Discover (Validated via Luhn algorithm) <CREDIT_CARD_n>
Government Identifiers US SSN (XXX-XX-XXXX), UK NINO, Indian PAN Card <GOV_ID_n>
Personal Contact Data Email Addresses, E.164 International Phone Numbers, IPv4 / IPv6 <EMAIL_n> / <PHONE_n>

The Necessity of Client-Side AI Guardrails

As engineering teams, legal professionals, and financial analysts integrate generative AI into daily workflows, unvetted prompts routinely cause severe data leaks. Commercial LLM providers log input prompts for inference monitoring, compliance auditing, and downstream model reinforcement learning.

1. Why Deletion is Worse Than Pseudonymization

If you completely erase variables from code or prompts, the AI model loses syntactic context and hallucinates missing parameters. By replacing sensitive entities with structured synthetic tokens (e.g. <API_KEY_1> or <EMAIL_1>), the model accurately analyzes logic while leaving real credentials unexposed.

2. In-RAM Luhn Checksum & Regex Validation

To avoid false positives, credit cards are verified client-side using the **Luhn Checksum Formula**:

$$\sum_{i=0}^{n-1} d_i \equiv 0 \pmod{10}$$

This ensures random numeric strings are not unnecessarily masked while ensuring genuine payment details are caught.

🔐 Privacy Text Encryptor

Encrypt confidential text with AES-256-GCM via Text Encryptor Studio.

🛡️ Email Privacy Risk Checker

Audit email handle identity leakage with Email Risk Checker.

Frequently Asked Questions

Are prompts or code snippets uploaded to a server for scanning?

No. All scanning, regex evaluations, and token replacements run 100% locally in your device's browser memory (RAM).

How do I restore my original secrets after getting the AI response?

Keep this tab open while chatting with the AI. When the model returns its code or answer with the synthetic tokens (e.g. <API_KEY_1>), use the substitution map on the right to swap the real values back.

Ad Placement / In-Feed Responsive Unit