Skip to content
View Coff0xc's full-sized avatar
45 followers · 2 following
  • Security
  • China

Achievements

Achievement: Pull SharkAchievement: Starstruckx2

Achievements

Achievement: Pull SharkAchievement: Starstruckx2

Highlights

  • Pro

Block or report Coff0xc

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Coff0xc/README.md

Typing SVG


    

$ whoami
coff0xc — AI red teamer. I build weapons that test LLM/Agent systems,
then open-source them so defenders can catch up.

$ cat /etc/targets
LLM Jailbreak → Prompt Injection → Agent Hijacking → MCP Exploitation → Tool Poisoning

$ uname -a
Python 3.x | Rust | MCP Protocol | 9 Platforms | 18 Model Adapters

Weapons Cache

Everything I build is open-source. Attacks belong to defenders.

AutoRedTeam-Orchestrator  
Enterprise AI Red Team Platform — 132 MCP Tools · SDK+CLI+MCP · Docker Sandbox · SARIF CI/CD

catchclaw  
Multi-platform Agent Security — 78 DAG Attack Chains · 78 Exploits · ATT&CK Mapping · Rust

LLM-Security-Assessment-Framework  
FORGEDAN — Evolutionary LLM Assessment · 6 Attack Methods · 18 Model Adapters · Vue 3

CTF-MCP  
MCP Server for CTF — 126 Tools · Web / Crypto / Pwn · Automated Challenge Solving

Github-API-scan  
GitHub API Key Scanner — OpenAI/Claude/Gemini/Azure · Async Validation · Balance Detection

coffee-skill  
Codex/Agent Workflow Skill Pack — Dev · Agent/RAG · API/Data · Security Review

Arsenal

Activity

streak

 

Contributions

contribution snake 
 ██████╗ ██████╗ ███████╗███████╗ ██████╗ ██╗  ██╗ ██████╗
██╔════╝██╔═══██╗██╔════╝██╔════╝██╔═████╗╚██╗██╔╝██╔════╝
██║     ██║   ██║█████╗  █████╗  ██║██╔██║ ╚███╔╝ ██║
██║     ██║   ██║██╔══╝  ██╔══╝  ████╔╝██║ ██╔██╗ ██║
╚██████╗╚██████╔╝██║     ██║     ╚██████╔╝██╔╝ ██╗╚██████╗
 ╚═════╝ ╚═════╝ ╚═╝     ╚═╝      ╚═════╝ ╚═╝  ╚═╝ ╚═════╝

"The best way to secure a system is to try to break it."

Pinned Loading

  1. AutoRedTeam-Orchestrator AutoRedTeam-Orchestrator Public

    Enterprise AI Red Team Platform | 企业级AI红队平台 | 132 MCP Tools | Pure Python Engines | SDK+CLI+MCP | Auto-Download sqlmap/nuclei/ffuf | Production C2 | LLM Enhanced | Docker Sandbox | SARIF CI/CD | 19…

    Python 233 52

  2. Github-API-scan Github-API-scan Public

    GitHub 泄露的 API 密钥扫描器。支持 OpenAI/Claude/Gemini/Azure。异步验证 + GPT-4 探测 + 余额检测。丰富的 TUI 控制面板。

    Python 42 24

  3. LLM-Security-Assessment-Framework LLM-Security-Assessment-Framework Public

    FORGEDAN — An Evolutionary Framework for LLM Security Assessment | 6 Attack Methods | 18 Model Adapters | Vue 3 Dashboard | Web Security Scanning

    Python 22 8

  4. CTF-MCP CTF-MCP Public

    MCP Server for CTF challenges - 126 tools for Web/Crypto/Pwn | CTF 挑战 MCP 服务器 - Web/密码学/二进制利用工具集

    Python 19 9

  5. catchclaw catchclaw Public

    CatchClaw v5.3.0 — 多平台 AI Agent 安全评估工具，支持 OpenClaw / Dify / FastGPT / LobeChat / NextChat / AnythingLLM / Flowise / RagFlow 等 9 大平台。78 条 DAG 攻击链 | 78 个 Exploit 模块 | ATT&CK 阶段映射 | 多平台指纹识别 | Async To…

    Rust 23 5

  6. coffee-skill coffee-skill Public

    Installable Codex/AgentSkills workflow pack for dev, Agent/RAG, API/data, Office artifacts, research diagrams, and authorized security review.

    Python 11