← Discover
GitHub · Tencent/AI-Infra-Guard

Security audit for your AI infrastructure

AI-Infra-Guard is an end-to-end AI red team platform that scans agents, skills, MCP, and AI infrastructure, as well as performs LLM jailbreak assessments.

Updates

  • October 22, 2026: Stars 6,878 → 6,935, latest release v4.6.7 (October 22, 2026).
  • October 15, 2026: Stars 6,788 → 6,878, latest release v4.6.6 (October 15, 2026).
  • October 8, 2026: Stars 6,650 → 6,788, latest release v4.6.5 (October 8, 2026).
  • October 1, 2026: Stars 6,595 → 6,650, latest release v4.6.4 (October 1, 2026).

What you get

  • Scans for vulnerabilities in artificial intelligence systems.
  • Analyzes agent capabilities and model security.
  • Provides protection against jailbreak attacks.

Installation

Quick installation with Docker
git clone https://github.com/Tencent/AI-Infra-Guard.git
cd AI-Infra-Guard
# For Docker Compose V2+, replace 'docker-compose' with 'docker compose'
docker-compose -f docker-compose.images.yml up -d
Automatic installation with one command
curl https://raw.githubusercontent.com/Tencent/AI-Infra-Guard/refs/heads/main/docker.sh | bash

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

How can I detect vulnerabilities in my artificial intelligence infrastructure using the AI-Infra-Guard platform? Explain the steps I need to follow to initiate the skill scanning and jailbreak evaluation processes, especially in agent-based systems.

Repository: https://github.com/Tencent/AI-Infra-Guard. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

JailbreakMCPLLMArtificial Intelligence
Who it is forIt is for software developers and security experts who develop artificial intelligence models and agent-based systems and want to proactively monitor infrastructure security.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-20: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.