Canary token

Detect canary tokens that should not appear in user-visible output.

YAML key: canary_token
Direction: output

Detect canary tokens that should not appear in user-visible output.

Configuration

Prop

Type

defend.config.yaml (fragment)

guards:
  output:
    enabled: true
    provider: claude
    modules:
      - "canary_token"

Configure under guards.output.modules with output guarding enabled and provider claude or openai.

Malicious url

Detect malicious, deceptive, or unsafe URLs in model output.

Code execution output

Flag dangerous code execution patterns in model output.