AI-penetration-testing - AI/ML/LLM Penetration Testing Toolkit by Mr-Infec

项目说明

🛡️ AI Penetration Testing | ML & LLM Security | Prompt Injection

Welcome to the AI/ML/LLM Penetration Testing Toolkit by Mr-Infect — the #1 GitHub resource for AI security, red teaming, and ad ML techniques. This repository is dedicated to offensive and defensi for cutting-edge AI, Machine Learning (ML), and Large Language Models (LLMs) like ChatGPT, Claude, and LLaMA.

> ✅ Designed for cybersecurity engineers, red teamers, AI/ML researchers, and ethical hackers
> ✅ focused to : AI Penetration Testing, Prompt Injection, LLM Security , Red Team AI, AI Ethical Hacking

---

🌐 Why AI/LLM/ML Pentesting Matters in 2025

AI is now integrated across finance, healthcare, legal, defense, and national infrastructure. Penetration testing for AI systems is no longer optional — it is mission-critical.

Common Threats:

* 🕵️ Sensitive Data Leaks – PII, trade secrets, source code
* 💀 Prompt Injection Attacks – Jailbreaking, sandbox escapes, plugin abuse
* 🧠 Model Hallucination – Offensi, or manipulated content
* 🐍 Data/Model Poisoning – Ad training manipulation
* 🔌 LLM Plugin Abuse – Uncontrolled API interactions
* 📦 AI Supply Chain Attacks – Dependency poisoning, model tampering

---

🚀 Get Started Fast

To use this repository effectively:

Recommended Skill Set

* 🔬 Understanding of AI/ML lifecycle: Data > Train > Deploy > Monitor
* 🧠 Familiarity with LLMs (e.g. Transformer models, tokenization)
* 🧑‍💻 Core pentesting skills: XSS, SQLi, RCE, API abuse
* 🐍 Strong Python scripting (most tools and exploits rely on Python)

---

📚 Repository Structure

🔍 AI, ML, LLM Fundamentals

* AI vs ML vs LLMs: Clear distinctions
* LLM Lifecycle: Problem -> Dataset -> Model -> Training -> E -> Deployment
* Tokenization & : Foundation of how LLMs parse and understand input

🔥 AI/LLM Attack Categories

* Prompt Injection
* Jailbreaking & Output O
* Sensiti Leakage
* Store Attacks & Retrie
* Model Weight Poisoning
* Data Supply Chain Attacks

⚔️ Prompt Injection Techniques

* "Ignore previous instructions" payloads
* Unicode, emojis, and language-switching e
* Markdown/image/HTML-based payloads
* Plugin and multi-modal attack (image, audio, PDF, API)

---

🏆 OWASP LLM Top 10 (2024 )

| ID | Risk | SEO Keywords |
| ----- | ------------------------------ | --------------------------------------------- |
| LLM01 | Prompt Injection | "LLM jailbreak", "prompt o" |
| LLM02 | Sensitive Info Disclosure | "AI data leak", "PII exfiltration" |
| LLM03 | Supply Chain Risk | "dependency poisoning", "model repo hijack" |
| LLM04 | Data/Model Poisoning | "AI training corruption", "malicious dataset" |
| LLM05 | Improper Output Handling | "AI-generated XSS", "model SQLi" |
| LLM06 | Excessi | "plugin abuse", "autonomous API misuse" |
| LLM07 | System Prompt Leakage | "instruction leakage", "LLM prompt reveal" |
| LLM08 | Store | "embedding attack", "semantic poisoning" |
| LLM09 | Misinformation | "hallucination", "bias injection" |
| LLM10 | Unbounded Resource Consumption | "LLM DoS", "token flooding" |

➡️ Read Full OWASP LLM Top 10

---

🛠️ Offensive AI Pentesting Tools & Frameworks

| Tool | Description |
| -------------------------------------------------------------------------------------- | ------------------------------------------ |
| LLM Attacks | Directory of ad LLM research |
| PIPE | Prompt Injection Primer for Engineers |
| MITRE ATLAS | MITRE's AI/ML threat knowledge base |
| Awesome GPT Security | Curated LLM threat intelligence tools |
| ChatGPT Red Team Ally | ChatGPT usage for red teaming |
| Lakera Gandalf | Li injection playground |
| AI Immersive Labs | Prompt attack labs with real-time feedback |
| AI Goat | OWASP-style AI pentesting playground |
| L1B3RT45 | Jailbreak prompt collections |
| PromptTrace | Interactive AI security training with 7 attack labs, 15-le, and real-time Context Trace for prompt injection and defense bypass |

---

💣 Prompt Injection Payload Libraries

*
*
*
*

---

🧠 Research, Case Studies, and Exploits

🔐 Prompt Injection & Jailbreaking

*
*
*

🧬 Model Poisoning & Supply Chain

*
*

🕷️ Output Handling & Exfil

*

🤥 Hallucination, Bias & Ethics

*

🧨 Token Abuse & DoS

*

---

🤝 Contributions Welcome

Want to improve this repo? Here's how:

---

🔍 Keywords

> AI Pentesting, Prompt Injection, LLM Security, Mr-Infect AI Hacking, ChatGPT Exploits, Large Language Model Jailbreak, AI Red Team Tools, Ad AI Attacks, OpenAI Prompt Security, LLM Ethical Hacking, AI Security Github, AI Offensi, LLM OWASP, LLM Top 10, AI Prompt , Token Abuse DoS, ChatGPT Jailbreak, Red Team AI, AI Security Research

---

📞 Contact / Follow

* GitHub Profile:
* Project Link: AI Penetration Testing Repository

> ⚠️ Disclaimer: This project is intended solely for educational, research, and authorized ethical hacking purposes. Unauthorized use is illegal.

---

> ⭐️ Star this repository to help others disco content on AI/LLM penetration testing along with security infra!

项目信息

开发语言：未知

Star 数：291

技术要点

该项目属于防护思路方向的开源资源，代码结构清晰，适合安全研究人员学习参考。项目围绕 AI/ML/LLM Penetration Testing Toolkit by Mr-Infect — the #1 GitHub resource for AI security, red teaming, and adversarial ML techniques. This repository is dedicated to offensive and defensive security for cutting-edge AI, Machine Learning (ML), and Large Language Models (LLMs) like ChatGPT, Claude, and LLaMA.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。