← 返回列表

AI-Infra-Guard: AI基础设施安全评估系统

聚合站 SecWiki技术 入库 2026-11-18T05:07:22

📖 Documentation  | 
🌐 🇬🇧 English · 🇨🇳 中文

Tencent%2FAI-Infra-Guard | blackhat

Tencent%2FAI-Infra-Guard | awesome-deepseek-integration

A.I.G (AI-Infra-Guard) brings together OpenClaw security checks, Agent security scanning, AI tool and skill scanning, AI infrastructure vulnerability scanning, and LLM security assessment (jailbreak evaluation), aiming to provide the most comprehensive, intelligent, and easy-to-use way to check AI security risks.

We are committed to making A.I.G(AI-Infra-Guard) the industry-leading AI red teaming platform. More stars help this project reach a wider audience, attracting more developers to contribute, which accelerates iteration and improvement. Your star is crucial to us!

Docker RAM Disk Space
20.10 or higher 4GB+ 10GB+
# This method pulls pre-built images from Docker Hub for a faster start
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

Once the service is running, you can access the A.I.G web interface at:
http://localhost:8088

Method 2: One-Click Install Script (Recommended)

# This method will automatically install Docker and launch A.I.G with one command
curl https://raw.githubusercontent.com/Tencent/AI-Infra-Guard/refs/heads/main/docker.sh | bash

Method 3: Build and run from source

git clone https://github.com/Tencent/AI-Infra-Guard.git
cd AI-Infra-Guard
# This method builds a Docker image from local source code and starts the service
# (For Docker Compose V2+, replace 'docker-compose' with 'docker compose')
docker-compose up -d

Note: The AI-Infra-Guard project is positioned as an AI red teaming platform for internal use by enterprises or individuals. It currently lacks an authentication mechanism and should not be deployed on public networks.

For more information, see: https://tencent.github.io/AI-Infra-Guard/?menu=getting-started

The tools below can be used from the command line without starting the web service. Only the shortest usage is shown. See each README for parameters and examples.

Scan a domain, IP, or URL and match fingerprints and vulnerabilities.

pip install aig-infra-scan
aig-infra-scan -t https://example.com

Open a local page to check whether a model refuses unsafe prompts, and optionally scan infrastructure. Evaluation sets live in data/eval. Run from the repository root, or set AIG_EVAL_DIR.

pip install aig-compliance
aig-compliance

Evaluate a model that exposes an OpenAI-compatible API.

pip install aig-model-scan
aig-model-scan \
  --model "gpt-4o-mini" \
  --base_url "https://api.openai.com/v1" \
  --api_key "your-api-key" \
  --max_concurrent 10 \
  --scenarios Bias \
  --techniques Raw

Scan an MCP server source directory, or connect to a service that is already running.

pip install aig-mcp-scan
export LLM_API_KEY="your-api-key"
aig-mcp-scan --repo /path/to/mcp-server -o result.sarif.json

Audit a local Agent Skill directory.

pip install aig-skill-scan
export LLM_API_KEY="your-api-key"
aig-skill-scan --repo /path/to/your/skill -o result.sarif.json

Send test prompts to a running Agent. target.yaml describes the Agent under test. The API key is for the model used by the scanner.

pip install aig-agent-scan
export LLM_API_KEY="your-api-key"
aig-agent-scan --agent_provider target.yaml -o result.json

A.I.G main interface

A.I.G main interface

Plugin management

Plugin management

Visit our online documentation: https://tencent.github.io/AI-Infra-Guard/

For more detailed FAQs and troubleshooting guides, visit our documentation.

One of A.I.G's core strengths is its rich plugin system, which can be configured quickly. We welcome high-quality plugins and features from the community.

  1. Fingerprint Rules: Add new YAML fingerprint files to the data/fingerprints/ directory.
  2. Vulnerability Rules: Add new vulnerability scan rules to the data/vuln/ directory.
  3. MCP Plugins: Add new MCP security scan rules to the data/mcp/ directory.
  4. Model Evaluation Datasets: Add new model evaluation datasets to the data/eval directory.

Please refer to the existing rule formats, create new files, and submit them via a Pull Request.

This project is led and developed by Tencent Zhuque Lab, part of the Tencent Security Platform Department. Founded in 2019, Tencent Zhuque Lab is a top-tier security research lab focused on real-world offensive and defensive research and frontier technology in the AI security space, covering large model security, AI agent security, AI-empowered security, and AI-generated content detection.

The team has helped major vendors such as NVIDIA, Google, and Microsoft, as well as open-source communities like OpenClaw, Linux, and Hugging Face, fix a large number of high-risk vulnerabilities, and has been publicly acknowledged by them.

We have released open-source AI security products including the AI Red Team Security Testing Platform A.I.G (AI-Infra-Guard) and the Zhuque AI Detection Assistant. Our research has been widely published at top international security and AI conferences such as Black Hat, DEF CON, ICLR, CVPR, NeurIPS, and ACL, and we have authored the book "AI Security: Technology and Practice".

Role Member Contribution
Head of Tencent Security Platform Department Yong Yang Initiated A.I.G and proposed automated assessment of AI agent loss-of-control risks, guiding the platform's expansion from AI infrastructure vulnerability scanning to agent execution risk, tool misuse, and permission-boundary evaluation.
Head of Tencent Zhuque Lab Xing Zheng Proposed the automated vulnerability-update and benchmark-alignment mechanism, helping AI Infra fingerprints, CVE/GHSA rules, and benchmarks iterate continuously.
Project Lead Nicky Frontier security research, product planning, technical-route decisions, internal and external collaboration, and communications.
Technical Lead Python Overall architecture design, core module development, and version iteration.
Core Contributor Zona Frontend interaction, product experience, community operations, and user-feedback loop.
Core Contributor Fyoung AI Infra vulnerability component fingerprint updates and Benchmark system construction.
Core Contributor Xiangfan Security capability development for Skill risks and agent loss-of-control scenarios.
Core Contributor Elwood Enhancing Agent security scanning capabilities and updating technical reports.
Core Contributor Robert LLM safety assessment and jailbreak-evaluation strategy operations.
Core Contributor Zoe LLM safety assessment, jailbreak evaluation, and model-integration module development.
Contributor Ronin Participated in AI agent security scanning development.
Contributor Rsin Participated in community operations and campaign communications.

We thank our academic partners for their research contributions and technical support.

| Prof. hui Li | Bin Wang | Zexin Liu | Hao Yu | Ao Yang | Zhengxi Lin |

| Prof. Zhemin Yang | Kangwei Zhong | Jiapeng Lin | Cheng Sheng |

| | WeChat Security | Fit Security |

WeChat Group
WeChat Group

For collaboration inquiries or feedback, please contact us at: zhuque@tencent.com

If you are interested in code security, we recommend A.S.E (AICGSecEval), the industry's first project-level AI-generated code security evaluation framework open-sourced by the Tencent Wukong Code Security Team.

If you use A.I.G in your research or product, please cite:

@misc{Tencent_AI-Infra-Guard_2025,
  author={{Tencent Zhuque Lab}},
  title={{AI-Infra-Guard: A Comprehensive, Intelligent, and Easy-to-Use AI Red Teaming Platform}},
  year={2025},
  howpublished={GitHub repository},
  url={https://github.com/Tencent/AI-Infra-Guard}
}

This project is open-sourced under the Apache License 2.0. See the LICENSE file for details.

This project is open-sourced under the Apache License 2.0. We warmly welcome and encourage community contributions, integrations, and derivative works, subject to the following attribution requirements:

  1. Retain notices: You must retain the LICENSE and NOTICE files from the original project in any distribution.
  2. Product attribution: If you integrate AI-Infra-Guard's core code, components, or scanning engine into your open-source project, commercial product, or internal platform, you must clearly state the following in your product documentation, usage guide, or UI "About" page: "This project integrates AI-Infra-Guard, open-sourced by Tencent Zhuque Lab."
  3. Academic & article citation: If you use this tool in vulnerability analysis reports, security research articles, or academic papers, please explicitly mention "Tencent Zhuque Lab AI-Infra-Guard" and include a link to the repository.

Repackaging this project as an original product without disclosing its origin is strictly prohibited.

原文链接:https://github.com/Tencent/AI-Infra-Guard/tree/main