红蓝攻防
点击放大
AI-Infra-Guard - A full-stack AI Red Teaming platform securing AI e
项目说明
<p align="center">
<h1 align="center"><img ="middle" width="400px" src="img/logo-full-new.png" alt="A.I.G"/></h1>
</p>
<p align="center">
<a href=" Documentation</a> |
🌐 <a href="./readme/README_ZH.md">🇨🇳 中文</a> · <a href="./readme/README_JA.md">🇯🇵 日本語</a> · <a href="./readme/README_ES.md">🇪🇸 Español</a> · <a href="./readme/README_DE.md">🇩🇪 Deutsch</a> · <a href="./readme/README_FR.md">🇫🇷 Français</a> · <a href="./readme/README_KR.md">🇰🇷 한국어</a> · <a href="./readme/README_PT.md">🇧🇷 Português</a> · <a href="./readme/README_RU.md">🇷🇺 Русский</a>
</p>
<p align="center">
<a href="
<img src=" alt="GitHub stars">
</a>
<a href="
<img alt="GitHub downloads" src="
</a>
<a href="
<img alt="docker pulls" src="
</a>
<a href="
<img alt="Release" src="
</a>
<a href="
<img src=" alt="Ask DeepWiki">
</a>
</p>
<p align="center">
<a href=" target="_blank">
<img src=" alt="EdgeOne ClawScan">
</a>
<a href=" target="_blank">
<img src=" alt="EdgeOne Skill Scanner">
</a>
<a href=" target="_blank">
<img src=" alt="AIG Scanner">
</a>
</p>
<p align="center">
<a href=" target="_blank">
<img src=" alt="OpenClaw Recommended">
</a>
</p>
<p align="center">
<a href=" target="_blank"><picture><source media="(prefers-color-scheme: dark)" srcset=" media="(prefers-color-scheme: light)" srcset=" src=" alt="Tencent%2FAI-Infra-Guard | Trendshift" width="250" height="55"/></picture></a>
<a href=" target="_blank"><img src="img/blackhat.png" alt="Tencent%2FAI-Infra-Guard | blackhat" width="175" height="55"/></a>
<a href=" target="_blank"><img src="img/awesome-deepseek.png" alt="Tencent%2FAI-Infra-Guard | awesome-deepseek-integration" width="273" height="55"/></a>
</p>
<br>
<p align="center">
<h2 align="center">🚀 AI Red Teaming Platform by Tencent Zhuque Lab</h2>
</p>
<b>A.I.G (AI-Infra-Guard)</b> integrates capabilities such as ClawScan(OpenClaw Security Scan), Agent Scan，AI infra scan, MCP Server & Agent Skills scan, and Jailbreak E, aiming to provide users with the most comprehensi, and user-friendly solution for AI security risk self-examination.
<p>
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 de to contribute, which accelerates iteration and impro. Your star is crucial to us!
</p>
<p align="center">
<a href="
<img src=" alt="Give us a Star">
</a>
</p>
<br>
📋 User Feedback Survey
Help us improve A.I.G! Please take 3-5 minutes to fill out our User Feedback Survey. Users who provide high-quality feedback and leave a valid email address will receive an exclusi souvenir gift.
<br>
🚀 What's New
👉 Earlier releases · 🛒 AI Security Skill Market · 🔍 skill-scan CLI · 🔍 mcp-scan CLI · 🔍 agent-scan CLI · 📊 SkillTrustBench
Table of Contents
<br><br>
🚀 Quick Start
🐳 Deploy A.I.G with Docker
| Docker | RAM | Disk Space |
|:-------|:----|:----------|
| 20.10 or higher | 4GB+ | 10GB+ |
Once the service is running, you can access the A.I.G web interface at:
<br>
#### Use from OpenClaw
You can also call A.I.G directly from OpenClaw chat via the aig-scanner skill.
Then configure AIG_BASE_URL to point to your running A.I.G service.
For more details, see the aig-scanner README.
<details>
<summary><strong>More installation options</strong></summary>
Other Installation Methods
Method 2: One-Click Install Script （Recommended）
Method 3: Build and run from source
Note: The AI-Infra-Guard project is positioned as an AI red teaming platform for internal use by enterprises or indi. It currently lacks an authentication mechanism and should not be deployed on public networks.
For more information, see:
</details>
⚡ Install aig-skill-scan with a Single Command
Agent Skill security audit tool, easily integrated into enterprise CI/CD pipelines. classification aligns with SkillTrustBench T01–T09 taxonomy. Learn more →
Model and API Relay Checker
The checker frontend is deployed separately. Docker deployment keeps the
checker APIs a at GET /api/v1/relay/models andPOST /api/v1/relay/check/stream; API documentation is a at. To run the checker and unified CLI
from source:
See the API Checker integration guide for
the Agent-embedded runtime architecture, HTTP API, configuration, and security boundaries.
🌟 Try the Online Pro
Experience the Pro with ad features and impro. The Pro requires an in code and is prioritized for contributors who ha issues, pull requests, or discussions, or actively help grow the community. Visit:
<br>
<br>
✨ Features
🔍 aig-skill-scan Performance & Co
Performance on SkillTrustBench with different LLMs:
| # | Model | F1 | Precision | Recall | FPR |
|:--|:------|:---|:----------|:-------|:----|
| 1 | Claude Opus 4.6 | 0.9848 | 0.9725 | 0.9974 | 0.0663 |
| 2 | GLM 5.1 | 0.9836 | 0.9701 | 0.9974 | 0.0723 |
| 3 | Gemini 3.5 Flash | 0.9792 | 0.9947 | 0.9641 | 0.0120 |
| 4 | Kimi 2.6 | 0.9780 | 0.9895 | 0.9667 | 0.0241 |
| 5 | DeepSeek v4 Flash | 0.9740 | 0.9868 | 0.9615 | 0.0301 |
Covers 9 categories of Skill security risks (SkillTrustBench T01–T09):
| Layer | Risks |
|:------|:--------|
| A · Instruction & Memory | T01 Skill Instruction Hijacking, T02 Memory Poisoning |
| B · Code Execution | T03 Remote Payload Download & Execution, T04 Embedded Malicious Code |
| C · System Pri | T05 Pri Escalation & Unauthorized Access, T06 System Persistence |
| D · Toolchain & Dependencies | T07 Tool Hijacking & Spoofing, T08 Insecure Dependencies |
| E · Skill Code Quality | T09 Insecure Coding Practices |
For full leaderboard and details, visit SkillTrustBench.
🔬 Security Scanning & E
| Feature | More Info |
|:--------|:------------|
| ClawScan(OpenClaw Security Scan) | Supports one-click e of OpenClaw security risks. It detects insecure configurations, Skill risks, C, and privacy leakage. |
| Agent Scan | This is an independent, multi-agent automated scanning framework. It is designed to e the security of AI agent workflows. It seamlessly supports agents running across platforms, including Dify and Coze. |
| MCP Server & Agent Skills scan | It thoroughly detects 14 major categories of security risks. The detection applies to both MCP Servers and Agent Skills. It flexibly supports scanning from both source code and remote URLs. |
| AI infra scan | This scanner precisely identifies over 100 AI framework components. It covers more than 2000 known C. Supported frameworks include Ollama, ComfyUI, vLLM, n8n, Triton Inference Server and more. |
| Jailbreak E | It assesses prompt security risks using carefully curated datasets. The e applies multiple attack methods to test robustness. It also provides detailed cross-model comparison capabilities. |
| Model and API Relay Checker | Model fingerprinting, Claude Signature , relay black-box auditing, PAMELA, and QTest. |
<details>
<summary><strong>💎 Additional Benefits</strong></summary>
</details>
<br />
🖼️ Showcase
A.I.G Main Interface
!A.I.G Main Page
Plugin Management
!Plugin Management
<br />
🗺️ Quick Usage Guide
> After deployment, open in your browser.
AI Infrastructure Scan
What to enter as the target URL / IP?
The target is the network address of a running AI service you want to scan - not a GitHub URL or source code path. A.I.G connects to the li and fingerprints it for known C.
| Scenario | Example target |
|:---------|:--------------|
| A locally running vLLM instance | |
| An Ollama server on your LAN | |
| A ComfyUI instance exposed internally | |
| Multiple hosts (one per line) | 192.168.1.0/24 (CIDR), 10.0.0.1-10.0.0.20 (range) |
Step-by-step: Scan a local vLLM instance
1. Start vLLM normally (e.g. python -m vllm.entrypoints.api_ser meta-llama/...)
2. In the A.I.G web UI, click "AI基础设施安全扫描 / AI Infra Scan"
3. Enter (or the IP/port where vLLM is listening)
4. Click Start Scan - A.I.G will fingerprint the service and match it against 2000+ known CVEs
5. View the report: component , matched , se, and remediation links
> 💡 Tip: To scan the *nightly* build of vLLM specifically, just run that nightly build and point A.I.G at its address. The scanner detects the automatically.
MCP Server & Agent Skills Scan
Enter either a remote URL (e.g. ) or upload a local source archive - no running instance required.
Jailbreak E
Configure the target LLM's API endpoint (base URL + API key) in Settings → Model Config, then select a dataset and start the e.
---
📖 User Guide
Visit our online documentation:
For more detailed FAQs and troubleshooting guides, visit our documentation.
<br />
<br>
🔧 API Documentation
A.I.G provides a comprehensive set of task creation APIs that support AI infra scan, MCP Server Scan, and Jailbreak E capabilities.
After the project is running, visit to view the complete API documentation.
For detailed API usage instructions, parameter descriptions, and complete example code, please refer to the Complete API Documentation.
<br />
<br>
📝 Contribution Guide
The extensible plugin framework serves as A.I.G's architectural cornerstone, in community inno through Plugin and Feature contributions.
Plugin Contribution Rules
1. Fingerprint Rules: Add new YAML fingerprint files to the
data/fingerprints/ directory.2. Rules: Add new scan rules to the
data/vuln/ directory.3. MCP Plugins: Add new MCP security scan rules to the
data/mcp/ directory.4. Jailbreak E Datasets: Add new Jailbreak e datasets to the
data/eval directory.Please refer to the existing rule formats, create new files, and submit them via a Pull Request.
Other Ways to Contribute
<br />
<br />
🛡️ About the Team
This project is led and de 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 defensi and frontier technology in the AI security space, co large model security, AI agent security, AI-empowered security, and AI-generated content detection.
The team has helped major 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 , and has been publicly acknowledged by them.
We ha open-source AI security products including the AI Red Team Security Testing Platform <b>A.I.G (AI-Infra-Guard)</b> 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 ha the book *"AI Security: Technology and Practice"*.
👥 Core Members & Contributions
| 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 scanning to agent execution risk, tool misuse, and permission-boundary e. |
| Head of Tencent Zhuque Lab | Xing Zheng | Proposed the automated 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 | O architecture design, core module de, and iteration. |
| Core Contributor | Zona | Frontend interaction, product experience, community operations, and user-feedback loop. |
| Core Contributor | Fyoung | AI Infra component fingerprint updates and Benchmark system construction. |
| Core Contributor | Xiangfan | Security capability de 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-e strategy operations. |
| Core Contributor | Zoe | LLM safety assessment, jailbreak e, and model-integration module de. |
| Contributor | Ronin | Participated in AI agent security scanning de. |
| Contributor | Rsin | Participated in community operations and campaign communications. |
<br />
🙏 Acknowledgements
🎓 Academic Collaborations
We thank our academic partners for their research contributions and technical support.
#### <img src="img/北大未来网络重点实验室2.png" height="30" align="middle"/>
<table>
<tr>
<td align="center" width="90">
<a href="#">
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="#">
<sub><b>Prof. hui Li</b></sub>
</a>
</td>
<td align="center" width="90">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Bin Wang</b></sub>
</a>
</td>
<td align="center" width="90">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Zexin Liu</b></sub>
</a>
</td>
<td align="center" width="90">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Hao Yu</b></sub>
</a>
</td>
<td align="center" width="90">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Ao Yang</b></sub>
</a>
</td>
<td align="center" width="90">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Zhengxi Lin</b></sub>
</a>
</td>
</tr>
</table>
#### <img src="img/复旦大学2.png" height="30" align="middle" style=": middle;"/>
<table>
<tr>
<td align="center" width="120">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Prof. Zhemin Yang</b></sub>
</a>
</td>
<td align="center" width="100">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Kangwei Zhong</b></sub>
</a>
</td>
<td align="center" width="90">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Jiapeng Lin</b></sub>
</a>
</td>
<td align="center" width="90">
<a href="
<img src=" width="70px;" style="border-radius: 50%;" alt=""/>
</a>
<br />
<a href="mailto:">
<sub><b>Cheng Sheng</b></sub>
</a>
</td>
</tr>
</table>
<br>
👥 Gratitude to Contributing De
Thanks to all the de who ha to the A.I.G project.
<br />
<table border="0" cellspacing="0" cellpadding="0">
<tr>
<td width="33%"><img src="img/keen_lab_logo.svg" alt="Keen Lab" height="85%"></td>
<td width="33%"><img src="img/wechat_security.png" alt="WeChat Security" height="85%"></td>
<td width="33%"><img src="img/fit_sec_logo.png" alt="Fit Security" height="85%"></td>
</tr>
</table>
<a href="
<img src=" />
</a>
<br>
<br>
🤝 Appreciation for Our Users
Thanks to the users from the following organizations and teams for using A.I.G and their feedback.
<br>
<di="center">
<img src="img/tencent.png" alt="Tencent" height="28px">
<img src="img/deepseek.png" alt="DeepSeek" height="38px">
<img src="img/antintl.svg" alt="Antintl" height="45px">
<img src="img/lenovo.png" alt="Lenovo" height="35px">
<img src="img/ICBC.jpg" alt="ICBC" height="40px">
<img src="img/vivo.png" alt="Vivo" height="30px">
<img src="img/oppo.png" alt="Oppo" height="30px">
<img src="img/haier.png" alt="Haier" height="30px">
<img src="img/abc.png" alt="Abc" height="40px">
<img src="img/JkO.png" alt="招商银行" height="40px">
<img src="img/中国电信.png" alt="中国电信" height="40px">
<img src="img/bilibili.jpg" alt="Bilibili" height="38px">
<img src="img/qunar.png" alt="Qunar" height="35px">
<img src="img/蜜雪冰城.png" alt="蜜雪冰城" height="40px">
<img src="img/IDG.webp" alt="IDG" height="55px">
<img src="img/kingdee.png" alt="kingdee" height="40px">
<img src="img/unicom.png" alt="联通数科" height="40px">
<img src="img/changan.png" alt="长安汽车" height="40px">
<img src="img/tiane.png" alt="天鹅到家" height="35px">
</div>
<di="center">
<img src="img/清华大学.jpg" alt="清华大学" height="40px">
<img src="img/北京大学.png" alt="北京大学" height="40px">
<img src="img/nanyang.png" alt="南洋理工大学" height="40px">
<img src="img/fudan.png" alt="复旦大学" height="40px">
<img src="img/浙江大学.png" alt="浙江大学" height="40px">
<img src="img/南京大学.png" alt="南京大学" height="40px">
<img src="img/wuhan.png" alt="武汉大学" height="40px">
<img src="img/An-NajahNationalUni.png" alt="An-Najah National Uni" height="40px">
<img src="img/西安交通大学.png" alt="西安交通大学" height="40px">
<img src="img/huazhong.png" alt="华中科技大学" height="45px">
<img src="img/南开大学.jpg" alt="南开大学" height="45px">
<img src="img/四川大学.png" alt="四川大学" height="40px">
<img src="img/Binus_Uni.svg" alt="Binus Uni" height="45px">
</div>
<br>
<br>
💬 Join the Community
🌐 Online Discussions
📱 Discussion Community
<table>
<thead>
<tr>
<th>WeChat Group</th>
<th>Discord <a href="]</a></th>
</tr>
</thead>
<tbody>
<tr>
<td><img src="img/wechatgroup.png" alt="WeChat Group" width="200"></td>
<td><img src="img/discord.png" alt="discord" width="200"></td>
</tr>
</tbody>
</table>
📧 Contact Us
For collaboration inquiries or feedback, please contact us at:
🔗 Recommended Security Tools
If you are interested in code security, check out A.S.E (AICGSecEval), the industry's first repository-le code security e framework open-sourced by the Tencent Wukong Code Security Team.
<br>
<br>
📖 Citation
If you use A.I.G in your research, please cite:
<br>
📚 Research & Papers
Research:
1. "RogueHandoff-20: Measuring Susceptibility to Unsafe Agent Trajectories" — A Docker-based benchmark measuring whether an agent adopts an unsafe trajectory supplied as preceding state, testing susceptibility after exposure to another agent's unsafe strategy. [[code]](./Research/roguehandoff20)
2. "FORGE-Bench: A Deterministic Benchmark for Loss of Control in Autonomous Agents" — A deterministic, oracle-based benchmark studying how autonomous agents lose control while pursuing legitimate tasks, e goal pressure, constraint degradation, and unsafe opportunity across 16 domains and 1,800 trajectories. [[arXi://arxiv.org/abs/2609.11024) [[code]](./Research/forge_bench)
3. "DeepSeek Harness Indirect Prompt-Injection Assessment" — Authorized security assessment of DeepSeek Harness against indirect prompt-injection across 14,560 agent runs. [[code]](./Research/deepseek-harness-security-assessment)
4. "SkillJack: Persistent Skill Backdoors in Self-E Agents" — Demonstrates how poisoned trajectories can inject persistent backdoors into self-e agent skill systems. [[code]](./Research/SkillJack)
Papers:
1. "Securing the AI Agent: A Unified Framework for Multi-Layer Agent Red Teaming" — A comprehensi for securing AI agent systems through multi-layer red teaming across infrastructure, supply chain, runtime interaction, and deployment surfaces. [[arXi://arxiv.org/pdf/2606.31227) [[pdf]](./Securing_the_AI_Agent.pdf)
2. "AI-Infra-Guard: An AI Red Teaming Platform" — Black Hat Europe 2025 Arsenal presentation showcasing A.I.G's capabilities and real-world use cases. [[pdf]](./Arsenal-BHEU2025-AI-Infra-Guard.pdf)
3. "MCP Unchained: Compromising The AI Agent Ecosystem Via Its Uni Connector" — Black Hat Europe 2025 talk re security risks in the MCP protocol within the AI agent ecosystem. [[pdf]](./BHEU-25-MCP-Unchained-Compromising-The-AI-Agent-Ecosystem-tor.pdf)
Thanks to the research teams who ha A.I.G in their academic work (19 papers):
<details>
<summary>📄 View all 19 cited papers</summary>
1. Chenning Li, Pan Hu, Justin Xu et al. "ADR: An Agentic Detection System for Enterprise Agentic AI Security." arXi arXiv:2605.17380 (2026). [[pdf]]()
2. Zhaojiacheng Zhou. "Proteus: A Self-E Red Team for Agent Skill Ecosystems." arXi arXiv:2605.11891 (2026). [[pdf]]()
3. Hengkai Ye, Zhechang Zhang, Jinyuan Jia et al. "TRUSTDESC: Pre Tool Poisoning in LLM Applications Description Generation." arXi arXiv:2604.07536 (2026). [[pdf]]()
4. Zenghao Duan, Yuxin Tian, Zhiyi Yin et al. "SkillAttack: Automated Red Teaming of Agent Skills through Attack Path Refinement." arXi arXiv:2604.04989 (2026). [[pdf]]()
5. Yiheng Huang, Zhijia Zhao, Bihuan Chen et al. "From Component Manipulation to System Compromise: Understanding and Detecting Malicious MCP Servers." arXi arXiv:2604.01905 (2026). [[pdf]]()
6. Yi Ting Shen, Kentaroh Toyoda, Alex Leung. "MCP-38: A Comprehensi Taxonomy for Model Context Protocol Systems (v1.0)." arXi arXiv:2603.18063 (2026). [[pdf]]()
7. Yuepeng Hu, Yuqi Jia, Mengyuan Li et al. "MalTool: Malicious Tool Attacks on LLM Agents." arXi arXiv:2602.12194 (2026). [[pdf]]()
8. Naen Xu, Jinghuai Zhang, Ping He et al. "FraudShield: Knowledge Graph Empowered Defense for LLMs against Fraud Attacks." arXi arXiv:2601.22485v1 (2026). [[pdf]]()
9. Ruiqi Li, Zhiqiang Wang, Yunhao Yao et al. "MCP-ITP: An Automated Framework for Implicit Tool Poisoning in MCP." arXi arXiv:2601.07395v1 (2026). [[pdf]]()
10. Jingxiao Yang, Ping He, Tianyu Du et al. "HogVul: Black-box Ad Code Generation Framework Against LM-based Detectors." arXi arXiv:2601.05587v1 (2026). [[pdf]]()
11. Teofil Bodea, Masanori Misono, Julian Pritzi et al. "Trusted AI Agents in the Cloud." arXi arXiv:2512.05951v1 (2025). [[pdf]]()
12. Yunyi Zhang, Shibo Cui, Baojun Liu et al. "Beyond Jailbreak: Un Risks in LLM Applications Arising from Blurred Capability Boundaries." arXi arXiv:2511.17874v2 (2025). [[pdf]]()
13. Bin Wang, Zexin Liu, Hao Yu et al. "MCPGuard: Automatically Detecting in MCP Servers." arXi arXiv:2510.23673v1 (2025). [[pdf]]()
14. Weibo Zhao, Jiahao Liu, Bonan Ruan et al. "When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation." arXi arXiv:2509.24272v1 (2025). [[pdf]]()
15. Ping He, Changjiang Li, et al. "Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools." arXi arXiv:2509.21011 (2025). [[pdf]]()
16. Christian Coleman. "Beha Detection Methods for Automated MCP Ser Assessment." (2025). [[pdf]]()
17. Yixuan Yang, Daoyuan Wu, Yufan Chen. "MCPSecBench: A Systematic Security Benchmark and Playground for Testing Model Context Protocols." arXi arXiv:2508.13220 (2025). [[pdf]]()
18. Yongjian Guo, Puzhuo Liu, et al. "Systematic Analysis of MCP Security." arXi arXiv:2508.12538 (2025). [[pdf]]()
19. Zexin Wang, Jingjing Li, et al. "A Survey on AgentOps: Categorization, Challenges, and Future Directions." arXi arXiv:2508.02121 (2025). [[pdf]]()
</details>
📧 If you have used A.I.G in your research or product, or if we ha missed your publication, we would love to hear from you! Contact us here.
<br>
<br>
⚖️ License & Attribution
This project is open-sourced under the Apache License 2.0. We warmly welcome and encourage community contributions, integrations, and deri 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 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.
<div>
<a href="
<picture>
<source media="(prefers-color-scheme: dark)" srcset=" />
<source media="(prefers-color-scheme: light)" srcset=" />
<img alt="Star History Chart" src=" />
</picture>
</a>
项目信息
开发语言：Python
Star 数：6753
技术要点
该项目属于红蓝攻防方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.展开，提供了可运行的实现，对理解相关安全机制、工具原理与攻防技术具有较高的研究价值。
从技术实现角度看，此类项目的核心在于对底层原理的深入理解与工程化落地。开发者在研究过程中可以结合官方文档与社区讨论，梳理项目的初始化流程、核心模块职责与数据流转，逐步掌握其中的技术细节与设计思路。
使用与学习建议
1. 下载源码压缩包，解压到本地环境。
2. 根据项目类型准备对应的运行环境与依赖。
3. 按照 README 中的步骤完成配置与部署。
4. 在隔离的测试环境中运行验证，避免影响生产系统。
免责声明
本资源来源于开源社区，仅供安全研究、技术学习与合法授权范围内的攻防演练使用，请勿用于任何非法或侵害他人权益的用途。使用本项目产生的一切后果由使用者自行承担。
| 资源标题 | AI-Infra-Guard - A full-stack AI Red Teaming platform securing AI e |
| 所属分类 | 红蓝攻防 |
| 发布作者 | admin |
| 发布时间 | 2026-10-06 00:33:00 |
| 下载权限 | 免费下载 |
| 附件数量 | 2 个下载链接 |
| 浏览次数 | 398 |
| 讨论数量 | 0 |
| 主题状态 | 正常讨论中 |