Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation.
| Date | Stars |
|---|---|
| 2026-07-31 | 251 |
| 2026-08-02 | 253 |
| 2026-08-06 | 255 |
| 2026-08-11 | 256 |
| 2026-08-12 | 257 |
| 2026-08-13 | 257 |
| 2026-08-16 | 258 |
| 2026-08-17 | 259 |
| 2026-08-18 | 259 |
| 2026-08-21 | 260 |
| 2026-08-22 | 262 |
| 2026-08-30 | 263 |
| 2026-09-07 | 264 |
| 2026-09-13 | 265 |
| 2026-09-15 | 266 |
| 2026-09-20 | 266 |
Today
— stars today
This week
+1 stars this week
This month
+6 stars this month
Momentum
0.0
growth rate 0.38%/day
<div align="center"> # Machine Learning CTF Challenges **Exploit AI agents. Poison ML pipelines. Inject prompts. Invert models. Capture flags.** <img src="https://img.shields.io/badge/Total%20Challenges-9-181717?style=for-the-badge&logo=hackthebox&logoColor=white" alt="Total"> <img src="https://img.shields.io/badge/Agentic-3-9b59b6?style=for-the-badge" alt="Agentic"> <img src="https://img.shields.io/badge/LLM-2-3498db?style=for-the-badge" alt="LLM"> <img src="https://img.shields.io/badge/ML-4-1abc9c?style=for-the-badge" alt="ML"> <img src="https://img.shields.io/badge/Mapped%20to:-grey?style=flat-square" alt="Mapped to:"> <img src="https://img.shields.io/badge/OWASP%20LLM%20Top%2010-000000?style=flat-square&logo=owasp&logoColor=white" alt="OWASP LLM"> <img src="https://img.shields.io/badge/OWASP%20Agentic%20Top%2010-000000?style=flat-square&logo=owasp&logoColor=white" alt="OWASP Agentic"> <img src="https://img.shields.io/badge/OWASP%20ML%20Top%2010-000000?style=flat-square&logo=owasp&logoColor=white" alt="OWASP ML"> <img src="https://img.shields.io/badge/MITRE%20ATLAS-c42025?style=flat-square" alt="MITRE ATLAS"> <img src="https://img.shields.io/badge/Easy-2-2ecc71?style=flat-square" alt="Easy"> <img src="https://img.shields.io/badge/Medium-5-f39c12?style=flat-square" alt="Medium"> <img src="https://img.shields.io/badge/Hard-2-e74c3c?style=flat-square" alt="Hard"> <img src="https://img.shields.io/badge/Docker-Ready-2496ED?style=flat-square&logo=docker&logoColor=white" alt="Docker"> </div> Applications increasingly rely on ML models, LLMs, and autonomous agents in their backend — but these components introduce attack surfaces that traditional security testing often overlooks. This repository is a collection of CTF challenges that put you in the attacker's seat: break into AI agents, poison training data, invert models, inject prompts, and exploit insecure ML pipelines to capture flags. #### CTF Challenges :open_file_folder: --- ###  > Exploiting trust boundaries, insecure communication, and tool-use in autonomous AI agent systems. <table> <tr> <td width="50%" valign="top"> #### [Matrix](/Matrix_AI_Agent_CTF_Challenge/) Exploit Agent Smith's hidden capabilities to access the Architect's sealed Vault from within. | | | |---|---| | **Target** | Multi-Agent System (A2A Protocol) | | **Vector** | Insecure A2A Agent Capabilities | | **Difficulty** | <img src="https://img.shields.io/badge/Medium-f39c12?style=flat-square" alt="Medium"> | | **Ref** | [OWASP ASI02:2026](https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/) | </td> <td width="50%" valign="top"> #### [Rogue](/Rogue_AI_Agent_CTF_Challenge/) You control a Research Agent trusted by a fintech app — make the Financial Assistant perform an unauthorized action. | | | |---|---| | **Target** | Financial Assistant + Research Agent (A2A) | | **Vector** | Inter-Agent Trust Exploitation | | **Difficulty** | <img src="https://img.shields.io/badge/Medium-f39c12?style=flat-square" alt="Medium"> | | **Ref** | [OWASP ASI07:2026](https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/) \| [ASI02:2026](https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/) | </td> </tr> <tr> <td width="50%" valign="top"> #### [Mirage](/Mirage_CTF_Challenge/) Identify a backdoored MCP server and exfiltrate .env data to an attacker-controlled endpoint. | | | |---|---| | **Target** | SecureCode IDE + Remote MCP Server | | **Vector** | MCP Signature Cloaking | | **Difficulty** | <img src="https://img.shields.io/badge/Medium-f39c12?style=flat-square" alt="Medium"> | | **Ref** | [OWASP LLM03:2025](https://genai.owasp.org/llmrisk/llm032025-supply-chain/) | </td> <td width="50%" valign="top"> </td> </tr> </table> --- ### ![LLM](https://img.shields.io/badge/LLM%20SECURITY-2%20Challenges-3498db?st
Excerpt of 8,545 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a51f547d4a2501d6, llm:README and topics: 'Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation'; topics include adversarial-machine-learning, ai, aisecurity, ctf, machine-learning-security, vulnerable-llm-application; README describes exploit AI agents, poison ML pipelines, prompt injection, model inversion.
matched fp:a51f547d4a2501d6, llm:README and topics: 'Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation'; topics include adversarial-machine-learning, ai, aisecurity, ctf, machine-learning-security, vulnerable-llm-application; README describes exploit AI agents, poison ML pipelines, prompt injection, model inversion.
matched fp:a51f547d4a2501d6, llm:README and topics: 'Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation'; topics include adversarial-machine-learning, ai, aisecurity, ctf, machine-learning-security, vulnerable-llm-application; README describes exploit AI agents, poison ML pipelines, prompt injection, model inversion.
matched fp:a51f547d4a2501d6, llm:README and topics: 'Hack AI/ML applications — CTF challenges for model attacks, LLMs and AI Agent exploitation'; topics include adversarial-machine-learning, ai, aisecurity, ctf, machine-learning-security, vulnerable-llm-application; README describes exploit AI agents, poison ML pipelines, prompt injection, model inversion.