> This page is for version Latest (default).
> For other versions, use one of these documentation indexes:
> - Latest (default): https://docs.nvidia.com/nemo/guardrails/latest/llms.txt
> - v0.25.0: https://docs.nvidia.com/nemo/guardrails/v0.25.0/llms.txt
> - v0.24.1: https://docs.nvidia.com/nemo/guardrails/v0.24.1/llms.txt
> - v0.24.0: https://docs.nvidia.com/nemo/guardrails/v0.24.0/llms.txt
> - v0.23.0: https://docs.nvidia.com/nemo/guardrails/v0.23.0/llms.txt
> - v0.22.0: https://docs.nvidia.com/nemo/guardrails/v0.22.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/guardrails/llms.txt.

# Zscaler AI Guard Integration

The Zscaler AI Guard guardrail uses the [Zscaler AI Guard](https://help.zscaler.com/ai-guard) API to scan prompts and LLM responses for security threats, including:

* **Credentials and secrets** - API keys, tokens, passwords, and cloud credentials
* **PII (Personally Identifiable Information)** - Names, emails, phone numbers, SSNs, and other personal data
* **Toxicity** - Violent, abusive, hateful, or harmful content
* **Prompt injection** - Adversarial prompts designed to manipulate AI behavior or bypass security controls
* **Malicious URLs** - Known malicious URLs and domains
* **Policy violations** - Custom content policy violations configured in the AI Guard console

The integration uses the [zscaler-sdk-python](https://pypi.org/project/zscaler-sdk-python/) SDK and implements **fail-closed** semantics: if the API call fails or returns an unexpected result, the integration blocks the content by default.

## Data handling

The input rail sends the full user message to the Zscaler AI Guard API. The output rail sends the full bot response. Review Zscaler's applicable privacy and data retention terms before enabling the integration in production.

## Configuration

Configure the integration with the following environment variables:

* `AIGUARD_API_KEY`: Required Zscaler AI Guard API key (Bearer token). To obtain this key, go to **AI Guard Console** > **Private AI Apps** > **Applications** > **API Keys**.
* `AIGUARD_CLOUD`: Optional cloud region. Options include `us1` (default), `us2`, `eu1`, and `eu2`.

To use a specific policy instead of automatic resolution, set the following optional variable:

* `AIGUARD_POLICY_ID`: Integer policy ID. When set, the integration calls `execute-policy` with the specified ID instead of `resolve-and-execute-policy`.

## Setup

### Colang v1

```yaml
# config.yml

# Optional: show detailed block messages (severity, policy name, detectors)
enable_rails_exceptions: true

rails:
  input:
    flows:
      - zscaler aiguard moderation on input

  output:
    flows:
      - zscaler aiguard moderation on output
```

### Colang v2

```yaml
# config.yml

colang_version: "2.x"
```

```text
# rails.co

import guardrails
import nemoguardrails.library.zscaler_aiguard

flow input rails $input_text
    zscaler aiguard moderation on input

flow output rails $output_text
    zscaler aiguard moderation on output
```

## How It Works

1. **Input scanning**: Before user prompts reach the LLM, the `zscaler aiguard moderation on input` flow sends the prompt to the AI Guard API with `direction="IN"`.
2. **Output scanning**: After the LLM generates a response, the `zscaler aiguard moderation on output` flow sends the response to the AI Guard API with `direction="OUT"`.
3. **Policy selection**: By default, the integration calls `resolve-and-execute-policy`, which automatically selects the appropriate policy. If `AIGUARD_POLICY_ID` is set, the integration calls `execute-policy` with the specified policy ID instead.
4. **Verdict handling**: If the API returns an `action` of `BLOCK`, the flow aborts and the bot refuses to respond. If the API returns `ALLOW` or `DETECT`, the content passes through normally.
5. **Rails exceptions**: Setting `enable_rails_exceptions: true` at the top level of the config causes blocked requests to emit a `ZscalerAiguardInputRailException` or `ZscalerAiguardOutputRailException`. The exception message contains the severity, policy name, blocking detectors, and transaction ID.
6. **Fail-closed**: If a scan fails because of a network error, timeout, or API error, the action returns a blocking `RailOutcome` with `failed=True`. Its metadata includes the error type without the provider's error details. This distinguishes a failed scan from a policy decision. `IORails` reports an internal-error response; the Colang flows follow their configured blocking behavior.

Missing `zscaler-sdk-python`, a missing `AIGUARD_API_KEY` when initializing the SDK client, or a non-integer `AIGUARD_POLICY_ID` raises a setup error from the action. `IORails` converts these action errors to failed blocking outcomes, while the Colang runtime reports an internal error. `IORails` checks for the SDK dependency at startup, so a missing SDK prevents compilation. Through the `Guardrails` facade, the default behavior is to fall back to `LLMRails`; set `require_iorails=True` to reject that fallback. Refer to [Rail Engine Support](/nemo/guardrails/reference/rail-engine-support#configuration-dependent-refusals).

## Detectors

The AI Guard policy engine evaluates all configured detectors and returns a single `ALLOW` / `BLOCK` / `DETECT` verdict. Available detectors include:

* `toxicity` - Toxic or harmful language
* `pii` - Personally identifiable information
* `personalData` - Personal data patterns
* `piiDeepscan` - Deep PII scanning
* `secrets` - Credentials, API keys, tokens
* `promptInjection` - Prompt injection attempts
* `maliciousUrl` - Malicious URL detection

Configure detectors in the [Zscaler AI Guard console](https://help.zscaler.com/aiguard), not in the NeMo Guardrails configuration.

## Dependencies

Install the required SDK:

```bash
pip install zscaler-sdk-python
```