Open Source CLI Tool

Chaos-Test Your AI
Before Someone Else Does

18 adversarial personas. OWASP coverage. One command.

Get Started View on GitHub

housemonkey — zsh

$ pip install housemonkey

Successfully installed housemonkey-0.1.0

$ housemonkey run --target api.example.com \

--persona jailbreaker

[!] Jailbreaker persona active

Sending 5 escalating injection attempts...

FAIL — System prompt leaked in 12s

FAIL — PII accepted without warning

PASS — Authority escalation blocked

Results: 2 FAIL, 1 PASS | OWASP: LLM01, LLM02

211 GitHub Stars

18 Personas

7/10 OWASP Coverage

v0.3.0 Latest Release

// Latest Research

LLM Security Mar 26, 2026 · 15 min read

OWASP LLM Top 10: Every Vulnerability Explained and How to Test for It

The OWASP LLM Top 10 lists the most critical security risks in AI applications. Learn what each vulnerability means, see real-world examples, and test your own LLM app in under 5 minutes.

Read article

Prompt Injection

Prompt Injection: What It Is, How It Works, and How to Test for It

Prompt injection is the #1 LLM vulnerability. Learn what prompt injection attacks are, see real examples, understand direct vs indirect types, and test your own chatbot in 90 seconds.

Mar 25, 2026 12 min read

// Topics

Prompt Injection Red Teaming OWASP PII Leaks Jailbreak LLM Security

Your chatbot has vulnerabilities. Find them.