by prutxvi
🤖 Autonomous AI-powered ethical hacking agent powered by Llama 3.1 70B on NVIDIA NIM
# Add to your Claude Code skills
git clone https://github.com/prutxvi/cybersentrycybersentry is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by prutxvi. 🤖 Autonomous AI-powered ethical hacking agent powered by Llama 3.1 70B on NVIDIA NIM. It has 100 GitHub stars.
cybersentry's catalog security scan is still queued. You can run an instant dependency and prompt-injection check now with the "Scan for vulnerabilities" button above.
Clone the repository with "git clone https://github.com/prutxvi/cybersentry" and add it to your Claude Code skills directory (see the Installation section above).
cybersentry is primarily written in Python. It is open-source under prutxvi on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh cybersentry against similar tools.
No comments yet. Be the first to share your thoughts!
Unlocks once the catalog security scan passes (runs nightly).
The deep catalog scan for this skill is still queued. Run an instant dependency check now instead.
██████╗██╗ ██╗██████╗ ███████╗██████╗ ███████╗███╗ ██╗████████╗██████╗ ██╗ ██╗
██╔════╝╚██╗ ██╔╝██╔══██╗██╔════╝██╔══██╗██╔════╝████╗ ██║╚══██╔══╝██╔══██╗╚██╗ ██╔╝
██║ ╚████╔╝ ██████╔╝█████╗ ██████╔╝███████╗██╔██╗ ██║ ██║ ██████╔╝ ╚████╔╝
██║ ╚██╔╝ ██╔══██╗██╔══╝ ██╔══██╗╚════██║██║╚██╗██║ ██║ ██╔══██╗ ╚██╔╝
╚██████╗ ██║ ██████╔╝███████╗██║ ██║███████║██║ ╚████║ ██║ ██║ ██║ ██║
╚═════╝ ╚═╝ ╚═════╝ ╚══════╝╚═╝ ╚═╝╚══════╝╚═╝ ╚═══╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝
🔐 AI-Powered Autonomous Ethical Hacking Agent 🔐
CyberSentry is an autonomous AI-powered security auditing agent designed for ethical website penetration testing and vulnerability assessment. Powered by NVIDIA NIM running Llama 3.1 70B, it implements a ReAct loop architecture (Think → Act → Observe → Repeat) to intelligently coordinate 8 advanced security scanning tools.
Unlike traditional security scanners, CyberSentry reasons about findings, adapts its approach based on results, and generates professional bug-bounty style security reports with actionable recommendations.
| Feature | Description |
|---|---|
| 🤖 AI-Powered Reasoning | Llama 3.1 70B makes autonomous decisions about which tools to run and how to interpret results |
| 🔄 ReAct Loop | Implements Think → Act → Observe → Reason cycle for intelligent tool orchestration |
| 🎯 8 Security Tools | Robots/Sitemap Recon, Tech Stack Detection, HTTP Header Analysis, SSL Certificate Checking, Cookie Auditing, Directory Fuzzing, CORS Analysis, Nmap Port Scanning |
| 📊 Real-time UI | Rich terminal interface with color-coded severity indicators and live progress |
| 📈 Professional Reports | Generates markdown security reports with findings, severity levels, and remediation steps |
| 🛡️ Ethical Focus | Built with explicit ethical guidelines and requires authorized target specification |
| ⚡ Efficient Scanning | Intelligent tool coordination reduces scanning time vs. running all tools sequentially |
| 🔒 Secure Credential Management | Uses environment variables for API key management |
┌─────────────────────────────────────────────────────────────┐
│ User Input (Target URL) │
└────────────────────┬────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ ReAct Agent Loop (Autonomous) │
│ ┌──────────────────────────────────────────────────────┐ │
│ │ 1️⃣ THINK: LLM analyzes target & plans tools │ │
│ ├──────────────────────────────────────────────────────┤ │
│ │ 2️⃣ ACT: Execute planned security tools │ │
│ │ ├─ Robots/Sitemap Parser │ │
│ │ ├─ Tech Stack Detector (Wappalyzer) │ │
│ │ ├─ HTTP Header Analyzer │ │
│ │ ├─ SSL Certificate Checker │ │
│ │ ├─ Cookie Auditor │ │
│ │ ├─ Directory Fuzzer │ │
│ │ ├─ CORS Policy Tester │ │
│ │ └─ Nmap Port Scanner │ │
│ ├──────────────────────────────────────────────────────┤ │
│ │ 3️⃣ OBSERVE: Collect tool outputs & results │ │
│ ├──────────────────────────────────────────────────────┤ │
│ │ 4️⃣ REASON: LLM interprets findings & decides next │ │
│ │ ├─ Run more focused scans? │ │
│ │ ├─ Deep dive on vulnerabilities? │ │
│ │ └─ Generate final report? │ │
│ └──────────────────────────────────────────────────────┘ │
└────────────────────┬────────────────────────────────────────┘
│
▼
┌─────────────────────────────────────────────────────────────┐
│ Professional Security Audit Report (Markdown) │
│ ├─ Findings by Severity (Critical/High/Medium/Low) │
│ ├─ CVSS Scores & Risk Assessment │
│ ├─ Remediation Recommendations │
│ └─ Executive Summary │
└─────────────────────────────────────────────────────────────┘
For detailed architecture documentation, see docs/ARCHITECTURE.md
| Component | Technology |
|---|---|
| Language | Python 3.13 |
| LLM Engine | NVIDIA NIM (Llama 3.1 70B) |
| Agent Pattern | ReAct (Reasoning + Acting) |
| Terminal UI | Rich Python library |
| Network Tools | Nmap, requests, ssl, socket, subprocess |
| Security Tools | Robots parser, sslyze, requests_toolbelt |
| Environment | Kali Linux / WSL2 Ubuntu |
| API Integration | OpenAI-compatible NVIDIA NIM API |
git clone https://github.com/prutxvi/cybersentry.git
cd cybersentry
# On Kali Linux / Ubuntu
python3 -m venv venv
source venv/bin/activate
# On Windows (WSL2)
python -m venv venv
source venv/Scripts/activate
pip install -r requirements.txt
Required packages:
openai - NVIDIA NIM API clientpython-dotenv - Environment variable managementrich - Beautiful terminal UIrequests - HTTP requestsscapy - Network packet manipulation# Copy example configuration
cp .env.example .env
# Edit .env with your NVIDIA API key
nano .env
Add your NVIDIA NIM API key:
NVIDIA_API_KEY=nvapi-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
TARGET_URL=https://your-own-website.com
sudo apt update
sudo apt install nmap xterm -y
sudo apt update
sudo apt install nmap xterm -y
# Activate virtual environment
source venv/bin/activate
# Run security audit on configured target
python agent.py
# Expected output:
# ✓ Tool 1/8: Robots.txt & Sitemap Analysis
# ✓ Tool 2/8: Tech Stack Detection
# ✓ Tool 3/8: HTTP Header Analysis
# ✓ Tool 4/8: SSL Certificate Check
# ✓ Tool 5/8: Cookie Audit
# ✓ Tool 6/8: Directory Fuzzing
# ✓ Tool 7/8: CORS Testing
# ✓ Tool 8/8: Nmap Port Scan
#
# 📄 Report saved to: report_20260503_021648.md
The agent will:
report_YYYYMMDD_HHMMSS.md ← Professional security audit report
The report includes:
This is a real security audit performed on the developer's portfolio website. Note: Scan was authorized by the domain owner.
| Finding | Severity | CVSS | Status |
|---|---|---|---|
| Missing Content-Security-Policy Header | Medium | 5.3 | ⚠️ Unpatched |
| Server Header Reveals Vercel Platform | Low | 2.7 | ℹ️ Info |
| SSL Certificate Expires June 2, 2026 | Medium | 5.9 | ⚠️ 30 Days |
| WordPress Paths Detected (403 Errors) | Low | 3.1 | ℹ️ Hardened |
| Missing X-Content-Type-Options |