Skip to main content
The Secure AI Gateway sits between your users and the AI providers and applies the following checks to every request and response.

​
Secret Detection

The gateway scans outgoing messages for credentials. If a secret is detected, the request is blocked before it reaches the AI provider. Detected secrets include:
  • API keys (OpenAI, AWS, GitHub, etc.)
  • Private keys (RSA, SSH, etc.)
  • Database connection strings
  • Bearer tokens

​
PII Detection & Masking

Personal Identifiable Information (PII) is detected automatically. Behavior is controlled by the pii parameter:
  • disabled: no scanning. For internal testing.
  • obfuscate: redacts sensitive data (e.g., [REDACTED_EMAIL]) and lets the conversation continue.
  • block: rejects the request if sensitive data is found.
Supported PII types:
  • Email addresses
  • Phone numbers
  • Credit card numbers
  • IP addresses
  • Social Security Numbers (SSN)

​
AI Firewall Rules

The gateway enforces organizational policies through firewall rules. Rules can:
  • Prevent the model from discussing certain topics.
  • Enforce specific personas or safety guidelines.
  • Restrict usage based on time or volume.

​
Audit Logs

Every API request is logged. Log entries include:
  • User ID / API key ID
  • Model used
  • Timestamp
  • Security check result (e.g., “Blocked by Secret Detection”)