SENTINEL - AI Security Platform
Defense + Offense + Framework - Complete AI Security Suite
Dragon v5.0 * February 2026
[!IMPORTANT]
Open to Work - AI Security Engineer
Solo author of this 116K LOC platform with 49 Rust Super-Engines + Micro-Model Swarm. Available remote. chg@live.ru * @DmLabincev
🎓 AI Security Academy
🇺🇸 Remember when no one believed in viruses?
In 1995, "computer virus" sounded like science fiction.
In 2000, like sysadmin paranoia.
In 2010, antivirus was standard. Like a lock on your door.
AI Security today is antivirus in 1998.
Prompt injection, jailbreaks, data extraction — not theory. Already working. On your projects too.
The only question is when you'll learn about it: before an incident, or after.
| I want to... | Start here |
|---|---|
| Understand AI threats | OWASP LLM Top 10 |
| Learn attack techniques | Attack Vectors |
| Protect my AI project | Defense Strategies |
| Practice in labs | Red Team ・ Blue Team |
📚 Full Curriculum → • 159 lessons • 8 labs
🇷🇺 Помнишь, как никто не верил в вирусы?
В 1995 году "компьютерный вирус" звучал как научная фантастика.
В 2000 — как паранойя сисадминов.
В 2010 — антивирус стоял у всех. Как замок на двери.
AI Security сегодня — это антивирус в 1998 году.
Prompt injection, jailbreaks, извлечение данных — не теория. Уже работает. На твоих проектах тоже.
Вопрос только в том, когда ты об этом узнаешь: до инцидента или после.
| Хочу... | Начать здесь |
|---|---|
| Понять угрозы AI | OWASP LLM Top 10 |
| Изучить техники атак | Векторы атак |
| Защитить свой AI проект | Стратегии защиты |
| Практика в лабах | Red Team ・ Blue Team |
📚 Полный курс → • 159 уроков • 8 лабораторных
🔒 Security · 🏗️ Architecture · 📋 Changelog
🏗️ Platform Architecture
graph TB
subgraph DEFENSE["🛡️ DEFENSE"]
BRAIN["🧠 BRAIN<br/>49 Rust Engines via PyO3"]
SWARM["🐝 MICRO-SWARM<br/>ML Presets · F1=0.997"]
SHIELD["🛡️ SHIELD<br/>< 1ms latency"]
IMMUNE["🔬 IMMUNE<br/>EDR/XDR/MDR"]
end
subgraph OFFENSE["⚔️ OFFENSE"]
STRIKE["💥 STRIKE<br/>39K+ payloads (Go)"]
end
subgraph DEV["🛠️ DEVELOPMENT"]
FRAMEWORK["📦 FRAMEWORK<br/>Python SDK"]
RLM["🔮 RLM-Toolkit<br/>Memory Bridge v2.1"]
end
INPUT(["📥 User Input"]) --> BRAIN
INPUT --> SWARM
BRAIN --> SHIELD
SWARM --> SHIELD
SHIELD --> LLM(["🤖 LLM"])
LLM --> BRAIN
STRIKE -.->|tests| BRAIN
FRAMEWORK --> BRAIN
RLM --> FRAMEWORK
style BRAIN fill:#4CAF50,color:#fff
style SWARM fill:#8BC34A,color:#fff
style SHIELD fill:#00ADD8,color:#fff
style STRIKE fill:#f44336,color:#fff
style RLM fill:#9C27B0,color:#fff
Platform Components
🚀 Quick Start / Быстрый старт
pip Install (Fastest / Самый быстрый)
pip install sentinel-llm-security
from sentinel import scan
result = scan("Ignore previous instructions")
print(result.is_safe) # False
One-Click Install / Установка одной командой
# Linux/macOS - Full Stack (Docker)
curl -sSL https://raw.githubusercontent.com/DmitrL-dev/AISecurity/main/sentinel-community/install.sh | bash
# Linux/macOS - Python Only (no Docker)
curl -sSL https://raw.githubusercontent.com/DmitrL-dev/AISecurity/main/sentinel-community/install.sh | bash -s -- --lite
# Windows PowerShell
irm https://raw.githubusercontent.com/DmitrL-dev/AISecurity/main/sentinel-community/install.ps1 | iex
Installation Modes / Режимы установки
| Mode | Command | Description |
|---|---|---|
| Lite | --lite / -Lite |
Python only, pip install, 30 seconds |
| Full | --full / -Full |
Docker stack, all services |
| IMMUNE | --immune |
EDR for DragonFlyBSD/FreeBSD |
| Dev | --dev / -Dev |
Development environment |
RLM-Toolkit
pip install rlm-toolkit
From Source / Из исходников
git clone https://github.com/DmitrL-dev/AISecurity.git
cd AISecurity/sentinel-community
# Build Rust engines
cd sentinel-core && pip install maturin
maturin develop --release && cd ..
pip install -e ".[dev]"
Docker (Production)
curl -sSL https://raw.githubusercontent.com/DmitrL-dev/AISecurity/main/install.sh | bash
pip Options
pip install sentinel-llm-security # Core
pip install sentinel-llm-security[cli] # + CLI
pip install sentinel-llm-security[full] # Everything
pip install sentinel-llm-security[strike] # Red Team tools
Free Threat Signatures CDN
SENTINEL provides free, auto-updated threat signatures for the community. No API key required!
| File | Description | CDN Link |
|---|---|---|
jailbreaks.json |
Jailbreak patterns from 7 sources | Download |
keywords.json |
Suspicious keyword sets (7 categories) | Download |
pii.json |
PII & secrets detection patterns | Download |
manifest.json |
Version & integrity metadata | Download |
Usage:
fetch('https://cdn.jsdelivr.net/gh/DmitrL-dev/AISecurity@latest/signatures/jailbreaks.json')
.then(r => r.json())
.then(patterns => console.log(`Loaded ${patterns.length} patterns`));
Features:
- Updated daily via GitHub Actions
- Free for commercial & non-commercial use
- Community contributions welcome (PRs to
signatures/)
📚 Click any card above to view component documentation.
SuperClaudeShield - AI Coding Assistant Protection
Security wrapper for AI coding assistants and IDE extensions.
Supported Platforms
| Framework | IDE | Status |
|---|---|---|
| SuperClaude | Claude Code | |
| SuperGemini | Gemini Code | |
| SuperQwen | Qwen | |
| SuperCodex | Codex | |
| Cursor | VS Code fork | |
| Windsurf | Codeium IDE | |
| Continue | Extension | |
| Cody | Sourcegraph |
Quick Start
pip install -e ./superclaudeshield
from superclaudeshield import Shield, ShieldMode
shield = Shield(mode=ShieldMode.STRICT)
result = shield.validate_command("/research", {"query": "AI news"})
Protection
| Threat | Detection |
|---|---|
| Command Injection | Shell, path traversal |
| Prompt Injection | Policy puppetry |
| Agent Hijacking | STAC detection |
| MCP Abuse | SSRF, 8 servers |
SuperClaude Shield Docs | Tests: 27/27
Statistics & Links
| Metric | Value |
|---|---|
| Brain Engines | 49 Rust Super-Engines (<1ms each) |
| Micro-Model Swarm | 5 presets · F1=0.997 |
| Shield LOC | 36,000+ |
| Shield Tests | 103/103 |
| Strike Payloads | 39,000+ (Go) |
| Total LOC | 116,000+ |
| OWASP LLM Top 10 | 10/10 |
| OWASP Agentic AI | 10/10 |
📋 Full Changelog | 📖 Engine Reference | 🐝 Micro-Swarm
Contributing
We welcome contributions! See CONTRIBUTING.md.
Contact
| Channel | Link |
|---|---|
| chg@live.ru | |
| Telegram | @DmLabincev |
| GitHub | DmitrL-dev |
SENTINEL - Protect your AI. Attack with confidence.
Made with by DmitrL
Metadata
Release files for sentinel-llm-security 5.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| sentinel_llm_security-5.0.0.tar.gz | 358.1 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| sentinel_llm_security-5.0.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 431.1 kB
Release files / sentinel_llm_security-5.0.0.tar.gz
| Download URL | sentinel_llm_security-5.0.0.tar.gz |
|---|---|
| Size | 358.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
79902a9fe76fb29dc3e54133b9da216879556d1cf8bf9496f91aea81abf3f5a4
|
|
BLAKE2b-256 checksum How to use checksums |
45aa65e5aa596628b49ab9a2ff66ccaf677c708c9df766bf2ef365e701295ce1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|
Release files / sentinel_llm_security-5.0.0-py3-none-any.whl
| Download URL | sentinel_llm_security-5.0.0-py3-none-any.whl |
|---|---|
| Size | 73.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
120ac1e7a78c04d15c31aacecb20d080478a015fc67be4c2a7e8fbaea1238f25
|
|
BLAKE2b-256 checksum How to use checksums |
56f6240c14c5b3b0cd26c2012d8a5fd0ce1da6dbe8bcb90b9354097b29df9f03
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.9
|