Zscaler AI Guard icon

Zscaler AI Guard

Scan AI prompts and responses for security threats using Zscaler AI Guard

Actions3

Response Scan

AI-generated

Summary

Scans provided text content for security threats using Zscaler AI Guard and returns detection results.

Inputs

  • content (required) — The text content to scan for security threats.
  • additionalOptions — A collection of options for the scan, including AI Model, Application Name, Environment, Max Retries, Policy ID Override, Timeout, Transaction ID, and User ID.

Output shape

A single JSON object per input item containing scan results, including detectors triggered, blocking status, severity, and metadata.

The response includes a 'blocked' boolean field (true if the scan result action is 'BLOCK') and an array of 'detectors' and 'blockingDetectors'. Metadata such as workflow ID, execution ID, and environment are added if provided.

Examples

Example 1: Scan a response text to check for policy violations.

Enter the response text in the 'Content' field and optionally set the 'Environment' in Additional Options.

Example 2: Force a specific policy ID for the scan.

Enter the content to scan and specify a 'Policy ID Override' in Additional Options.

Links

Discussion