Secrets

Detect likely secrets (API keys, tokens) in user input.

YAML key: secrets
Direction: input

Detect likely secrets (API keys, tokens) in user input.

Configuration

Prop

Type

defend.config.yaml (fragment)

guards:
  input:
    modules:
      - secrets:
          categories: []

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

Indirect injection

Detect indirect injection patterns from configured external sources.

Prompt leak

Detect leakage of system or developer prompts in model output.