NEWLeakSnitch v3.0 is almost hereSelf-serve protection for individuals. Fine-grained organizational rules for enterprises. Learn More

DETECTION RULES

Back to Home

What we block.

Every detection pattern is publicly transparent. No black boxes, no opaque rules - security teams can inspect, test, and verify every single pattern.

15+
AI Platforms Monitored
55+
Detection Patterns
3
Severity Tiers
100%
Pattern Transparency
Pattern Library

Detection patterns by category

All patterns are validated through regex matching, checksum validation (Luhn, Verhoeff), and Shannon entropy analysis to minimize false positives.

Credentials & Secrets

  • API Keys (AWS, GCP, OpenAI, Anthropic, Stripe, HuggingFace)
  • Tokens (JWT, OAuth, Bearer, Session Cookies, Base64 Auth)
  • Database URLs & SSH Private Keys
  • Slack Webhooks & S3/GCS Paths

Financial & Tax Data

  • Credit/Debit Cards (Luhn)
  • Bank Account + IFSC
  • UPI IDs
  • Payment QR Links
  • GSTIN, TIN, Invoice/Tax IDs

Personal & Corporate PII

  • Emails, Phone Numbers (US/IN), Aadhaar (Verhoeff), PAN, GPS
  • Employee/Student IDs, Medical/Insurance numbers
  • Internal .corp URLs, Confluence/Notion/SharePoint links
  • Google Analytics IDs, Browser Fingerprints

File scanning included

Detection isn't limited to typed prompts. LeakSnitch scans uploaded files - spreadsheets, config files, PDFs, Office documents, code archives - for the same sensitive patterns. File content is read locally, scanned in real time, and never leaves your device.

Disclosure & File Parsing

  • Natural language spills ("here is the secret...")
  • High-entropy strings (entropy > 4.5)
  • Parsed secrets from .env, JSON, YAML, and DevOps CI/CD configs
Platform Coverage

Monitored AI Platforms

ChatGPTClaudePerplexityGeminiDeepSeekQwenMidjourneyJasperCopy.aiWritesonicHugging FaceCharacter.aiPhindYou.comPoe
Scoring System

How detection severity works

Every detection is scored on a 0-100 scale. Context signals boost confidence, questions reduce it.

CriticalScore 80+

Definitive secret exposure - passwords, API keys, tokens, credentials

MediumScore 50-79

Potential sensitive data - phone numbers, addresses, internal URLs

LowScore < 50

Contextual signals - generic data patterns with lower confidence

Scoring modifiers

+15Context signal keyword nearby
+8Generic sensitive context nearby
-10Question mark at end (disclosure context)
-30Question mark at end (default)
-20Value shorter than 6 characters
+10Email with email-specific context
Get started

Try our platform today!

Real-time blocking across 18 AI platforms
55+ detection patterns with entropy validation
Enterprise dashboard with compliance reports
Free forever for individuals - upgrade when you scale
Install in 60 secondsZero Trust - Data never leavesNo credit card required