Zscaler AI Guard

Zscaler AI Guard integration for enforcing security policies on LLM inputs and outputs, including Data Loss Prevention (DLP) and prompt injection protection.

Zscaler AI Guard provides AI-powered security for LLM applications. It enforces Detections Policies to perform security checks such as Data Loss Prevention (DLP) and prompt injection protection on both inbound prompts and outbound model responses.

Get Started with Zscaler AI Guard

Using Zscaler AI Guard with Portkey

1. Add Zscaler Credentials to Portkey

• Navigate to the Plugins page under Admin Settings
• Click on the edit button for the Zscaler AI Guard integration
• Add your Zscaler AI Guard API Key (the DAS Application Key generated from your Zscaler AI Guard tenant)

2. Add Zscaler AI Guard Check

• Navigate to the Guardrails page and click the Create button
• Search for “Zscaler AI Guard” and click Add
• Configure your guardrail settings:
  • Policy ID: The ID of the Zscaler Detections Policy to execute (Required)
  • Timeout: The timeout in milliseconds for the scan (Default: 10000)
• Set any actions you want on your check, and create the Guardrail!

Guardrail Actions allow you to orchestrate your guardrails logic. You can learn more about them here

Check Name	Description	Parameters	Supported Hooks
Zscaler AI Guard Check	Scans prompts and responses against a Zscaler Detections Policy. Returns ALLOW or BLOCK based on the policy evaluation.	Policy ID (string), Timeout (number)	beforeRequestHook, afterRequestHook

3. Add Guardrail ID to a Config and Make Your Request

• When you save a Guardrail, you’ll get an associated Guardrail ID - add this ID to the input_guardrails or output_guardrails params in your Portkey Config
• Create these Configs in Portkey UI, save them, and get an associated Config ID to attach to your requests. More here.

Here’s an example config:

{
  "input_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"],
  "output_guardrails": ["guardrails-id-xxx", "guardrails-id-yyy"]
}

NodeJS

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY",
    config: "pc-***" // Supports a string config id or a config object
});

Python

portkey = Portkey(
    api_key="PORTKEY_API_KEY",
    config="pc-***" # Supports a string config id or a config object
)

OpenAI NodeJS

const openai = new OpenAI({
  apiKey: 'OPENAI_API_KEY',
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    apiKey: "PORTKEY_API_KEY",
    config: "CONFIG_ID"
  })
});

OpenAI Python

client = OpenAI(
    api_key="OPENAI_API_KEY",
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="openai",
        api_key="PORTKEY_API_KEY",
        config="CONFIG_ID"
    )
)

cURL

curl https://api.portkey.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
  -H "x-portkey-config: $CONFIG_ID" \
  -d '{
    "model": "gpt-5.1-nano",
    "messages": [{
        "role": "user",
        "content": "Hello!"
      }]
  }'

For more, refer to the Config documentation.

Your requests are now guarded by Zscaler AI Guard, and you can see the verdict and any actions taken directly in your Portkey logs!

Get Support

If you face any issues with the Zscaler AI Guard integration, join the Portkey community forum for assistance.