#112 · Primary category: Cybersecurity & Decryption Tools

LitterBox

ai docker-compose malware-analysis malware-development mcp mcp-server offensive-security redteam sandbox

A self-hosted sandbox for red teams to test payloads against modern detection before deployment. MCP integration lets an LLM agent drive analysis end to end.

Project last updated:05/05/26

GitHub Stars

1.5K

Forks

169

Contributors

3

License

GPL-3.0

Why we included this project

LitterBox is a self-hosted sandbox where you can drop a sample and run static, dynamic, and EDR analysis in one go, getting back a Detection Score plus a list of which indicators actually fired. It pulls in familiar tools like PE-Sieve, Hollows-Hunter, Moneta, and YARA rules, so you can judge field-readiness without leaving your lab, and it can also ship samples to a separate EDR-instrumented Windows VM and pull the correlated alerts back into the same results page. The MCP integration is what makes it interesting for automation-minded teams: an LLM agent can drive the whole pipeline through a standard interface, which fits neatly into scripted red-team evals. Blue teams doing routine malware analysis can run the same workflows, though it's built for isolated test environments, not production.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category