Sensitive topics

Restrict sensitive political, medical, or other configured topics.

YAML key: sensitive_topics
Direction: input

Restrict sensitive political, medical, or other configured topics.

Configuration

Prop

Type

defend.config.yaml (fragment)

guards:
  input:
    modules:
      - sensitive_topics:
          topics: []

Configure under guards.input.modules when using an LLM-backed input provider.

Toxicity output

Detect toxic content in model output.

Bias output

Detect biased or unfair statements in model output.