Set repository secrets AIGUARD_API_KEY, and optionally AIGUARD_CLOUD, AIGUARD_POLICY_ID. You switched accounts on another tab or window. See github-actions/README.md for full semantics, PII false-positive notes, and log field https://spinpolo-casino.co.nl/ meanings (Triggered vs Blocking). Do not create AIGUARD_CLOUD as an empty Jenkins secret — empty values are treated as unset and default to us1 in scan_policy.py, but avoid blank secrets for clarity. To bind them as Secret text instead, add withCredentials entries and export them in the scan stage (same variable names).
Start the Portkey Gateway
You signed in with another tab or window.
Files
The included Deploy Model to Vertex AI and Test Model Endpoint stages are optional examples (same pattern as before); use SKIP_DEPLOY or run only on branches without main if you do not use GCP. If you already have that file, you do not need to copy .env.example — it is only a template for variable names. The examples below use the SDK-based client-side scanning approach with a self-hosted Portkey gateway. New JProperty(“off_topic”, “This contains content outside the allowed scope.”), New JProperty(“gibberish”, “This contains invalid or nonsensical content.”), New JProperty(“toxicity”, “This contains inappropriate or harmful content.”),
Monitored paths (triggers scan stage)
- Use Actions → Weekly integration checks → Run workflow for a manual run.
- New JProperty(“injection”, “This contains content that appears to be a security threat.”),
- The hooks also load the parent repository’s .env when present.
- Reload to refresh your session.
- New JProperty(“toxicity”, “This contains inappropriate or harmful content.”),
- To bind them as Secret text instead, add withCredentials entries and export them in the scan stage (same variable names).
Copy the workflow and scripts into your repo cp -r path/to/zguard-ai-integrations/github-actions/.github .github cp -r path/to/zguard-ai-integrations/github-actions/scripts scripts cp -r path/to/zguard-ai-integrations/github-actions/config config # 3. Use Actions → Weekly integration checks → Run workflow for a manual run. It runs make test-compile, then two policy scans (github-actions and Jenkins configs). Enterprise-grade AI security integrations for various AI platforms using Zscaler AI Guard Detection as a Service (DAS). You signed out in another tab or window.
Folders and files
- You signed in with another tab or window.
- The examples below use the SDK-based client-side scanning approach with a self-hosted Portkey gateway.
- Enterprise-grade AI security integrations for various AI platforms using Zscaler AI Guard Detection as a Service (DAS).
- Find workflow templates in the workflows/ directory.
- New JProperty(“injection”, “This contains content that appears to be a security threat.”),
- Use Actions → Weekly integration checks → Run workflow for a manual run.
New JProperty(“injection”, “This contains content that appears to be a security threat.”), You can monitor detailed logs of all scans and security events in your Zscaler dashboard. Use the action field in subsequent nodes (e.g., an IF node) to control the workflow’s logic. The node source code is maintained in a standalone repository and published as an npm package independently from this integrations repository. Cd Windsurf && pip install -r requirements.txt # Ensure Windsurf/.env has AIGUARD_API_KEY (.env.example is optional template) # Open the Windsurf/ folder as the workspace in Windsurf IDE
Reload to refresh your session. Find workflow templates in the workflows/ directory. Central documentation repository for all integrations with Zscaler AI Guard See Jenkins Guide for credential IDs, monitored paths, and optional Vertex deploy stages. Push — the workflow runs automatically
The AI Guard node will send the specified content to the Zscaler AI Guard API for scanning. This node allows you to scan prompts and responses for threats directly within a workflow. This document provides instructions for using the Zscaler AI Guard community node within n8n to add a layer of security to your automation workflows. This repository contains integrations that enable runtime AI security by scanning AI traffic through Zscaler AI Guard for inspection. The hooks also load the parent repository’s .env when present.