Malicious URL

YAML key: malicious_url
Direction: output

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

Configuration

Example

guards:
  output:
    enabled: true
    provider: claude
    modules:
      - malicious_url:
          allowlist_domains: []
          allow_shorteners: []
          block_data_urls: true

Provider usage

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

See the modules overview.