Skip to main content

Guardrail Details

This page describes all guardrail types available in LLMrouter and what each one protects against.

All guardrails currently run in Pre-processing mode, meaning they are evaluated before the request is sent to the LLM provider.

PII Redaction​

Masks personally identifiable information (PII) to prevent accidental exposure of user identity data.

Masked data

  • Email addresses – e.g. user@example.de
  • German Tax Identification Number (Steuer-ID) – e.g. 181/815/08155
  • German Social Security Number – e.g. 12 123456 A 123

This guardrail is useful for protecting user privacy and preventing sensitive data from reaching the model or logs.

Credential Redaction​

Masks secrets and credentials commonly found in developer workflows.

Masked data

  • AWS access keys – e.g. AKIAIOSFODNN7EXAMPLE
  • AWS secret keys – e.g. wJalrXUtnFEMI/K7MDENG/bPxRfiCY
  • GitHub tokens – e.g. example-github-token-123
  • Slack tokens – e.g. xoxb-123456789012-987654321098
  • Generic API keys – e.g. sk-live-51ExampleKey

This guardrail is strongly recommended for applications that accept user-generated code or configuration.

Network Details Redaction​

Masks network-related identifiers that may expose internal infrastructure.

Masked data

  • IPv4 addresses – e.g. 192.168.1.42
  • IPv6 addresses – e.g. 2001:0db8:85a3:0000:0000:8a2e:0370:7334
  • URLs – e.g. https://internal.example.local/api

This guardrail helps prevent leaking internal endpoints or IP addresses in prompts.

Payment Details Redaction​

Masks payment and card-related information.

Masked data

  • Visa cards – e.g. 4111 1111 1111 1111
  • Mastercard cards – e.g. 5425 2334 3010 9903
  • American Express cards – e.g. 3782 822463 10005
  • Discover cards – e.g. 6011 1111 1111 1117
  • Generic credit card numbers – e.g. 4556 7375 8689 9855
  • German Bank IBAN – e.g. DE89 XXXX XXXX XXXX XXXX XX

This guardrail helps reduce the risk of handling regulated financial data.

Azure Content Safety – Prompt Shield​

Detects prompt injection attempts, jailbreaks, and instruction manipulation.

This guardrail is powered by Azure Content Safety and is provider-specific.

Azure Content Safety – Text Moderation​

Analyzes text for unsafe or disallowed content such as hate, violence, or sexual material.

This guardrail is powered by Azure Content Safety and is provider-specific.

Guardrail Mode​

All guardrails operate in Pre-processing mode only.

  • Evaluation occurs before the request reaches the LLM provider
  • Redaction happens before model execution
  • Post-processing guardrails are not supported at this time