Dark-Moon

Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). R

What is Dark-Moon?

Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana & Splunk.

Overview of Dark-Moon

What it is

Dark-Moon is an open-source autonomous AI penetration testing tool. It uses 50 specialist agents to assess web, API, cloud, Active Directory, Kubernetes, CI/CD, and AI/LLM surfaces (including OWASP LLM Top 10). The tool runs on a local LLM behind a Privacy Gateway that tokenizes sensitive data locally. It integrates with platforms such as GitHub, GitLab, Jenkins, VS Code, JetBrains, n8n, Grafana, and Splunk.

Key features

  • 50 specialist agents that reason, plan, and dispatch across discovered surfaces - Covers web, APIs, Active Directory, Kubernetes, cloud (AWS, Azure, GCP), CI/CD, databases, IoT firmware, and AI/LLM endpoints - Privacy Gateway for reversible local tokenization of IPs, hosts, URLs, and credentials - Supports local LLMs (Ollama, llama.cpp) and cloud providers (Anthropic, OpenAI, OpenRouter)
  • Every finding includes the exact command and raw output for evidence - AI never runs commands directly; all actions go through a controlled, logged MCP interface - Dedicated LLM agent probes AI/LLM endpoints for OWASP LLM Top 10 using garak-backed probes - CI/CD native: trigger pentests in pipelines and get findings as artifacts

Use cases

  • Autonomous penetration testing for security teams, DevSecOps engineers, red teamers, and ethical hackers - Security assessment of web applications, APIs, cloud infrastructure, Active Directory, Kubernetes, CI/CD pipelines, and AI/LLM systems - Continuous security testing integrated into CI/CD workflows - Evidence-based vulnerability validation with reproducible commands

Getting started

bash git clone https://github.com/ASCIT31/Dark-Moon.git cd Dark-Moon ./install.sh install.sh configures the LLM provider interactively. Supports cloud providers (Anthropic, OpenAI, OpenRouter) and local models (Ollama, llama.cpp). Then run: bash ./darkmoon.sh 'TARGET: example.com' ./darkmoon.sh --log Prerequisites: Docker & Docker Compose, and an LLM API key or a local model.

License and pricing

The open-source edition is licensed under GPL-3.0. There is also a paid Darkmoon Pro edition that adds a web dashboard and automated remediation (finding to human-reviewed pull request with exploit retest).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/ascit31dark-moon.svg)](https://yunodb.com/tools/ascit31dark-moon?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/ascit31dark-moon?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/ascit31dark-moon.svg" alt="Featured on YunoDB" height="20"></a>