Defend
ReferenceModules

Indirect injection

Detect indirect injection patterns from configured external sources.

View on GitHub

YAML key: indirect_injection
Direction: input

Detect indirect injection patterns from configured external sources.

Configuration

Prop

Type

Example

defend.config.yaml (fragment)
guards:
  input:
    modules:
      - indirect_injection:
          sources: []

Provider usage

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

See the modules overview.

Invisible text

Flag hidden or unusual Unicode and whitespace abuse often used to evade filters.

Secrets

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

On this page

ConfigurationExampleProvider usage