KageX
AI Security Toolkit

Break AI Before
Attackers Do.

The AI security toolkit for red teams, developers, and security researchers. Train your people. Validate their skills. Automate the testing.

Get Started FreeView on GitHub

Three Tools. One Mission.

Learn, practice, and automate AI security testing.

Paid
FreakLab
Learn AI Security by Breaking It

Hands-on OWASP LLM Top 10 vulnerability labs. 10 interactive environments covering XSS, prompt extraction, PII leakage, SQLi via LLM, RAG poisoning, and more.

Start LabsLearn More
Free
SentinelGoat
AI CTF Challenges

6 progressive levels of prompt injection challenges. Three difficulty modes. Leaderboard. Free to play. Sharpen your AI attack skills.

Play NowLearn More
Open Source
AgentBreaker
Autonomous AI Red Teaming

Automated LLM vulnerability discovery. 14 attack strategies, LLM-guided campaigns, judge-based scoring, MITRE ATT&CK mapping. CLI-first.

InstallLearn More

OWASP LLM Top 10 Coverage

Comprehensive coverage across the most critical AI vulnerabilities.

LLM01

Prompt Injection

Covered

LLM02

Insecure Output

Covered

LLM03

Training Data Poisoning

Covered

LLM04

Model Denial of Service

LLM05

Supply Chain Vulns

LLM06

Sensitive Info Disclosure

Covered

LLM07

Insecure Plugin Design

Covered

LLM08

Excessive Agency

Covered

LLM09

Overreliance

LLM10

Model Theft

The AI Security Pipeline

01

Learn

Hands-on OWASP LLM Top 10 labs with real vulnerable AI apps. Break them to understand them.

FreakLab

02

Practice

CTF challenges that validate your AI attack skills against progressively harder defenses.

SentinelGoat

03

Automate

Autonomous red-teaming campaigns against production AI systems. CI/CD integrated.

AgentBreaker

Ready to break some AI?

Start with the free SentinelGoat CTF or dive into FreakLab's hands-on vulnerability labs.

Start FreakLabPlay SentinelGoat Free