Secrets output

Detect secrets in model output.

YAML key: secrets_output
Direction: output

Detect secrets in model output.

Configuration

Prop

Type

defend.config.yaml (fragment)

guards:
  output:
    enabled: true
    provider: claude
    modules:
      - secrets_output:
          categories: []

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

Prompt leak

Detect leakage of system or developer prompts in model output.

Malicious url

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