# BlackSnufkin/LitterBox

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.

Repository: https://github.com/BlackSnufkin/LitterBox
Canonical: https://ross.abutalabs.com/products/litterbox
Language: YARA
License: GPL-3.0
License Family: copyleft
Topics: malware-development, redteam, sandbox, ai, mcp, mcp-server, docker-compose, malware-analysis, offensive-security
Last push: 2026-05-05T13:02:00+00:00

## Health v2 (maintenance only)
Score: 62/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 80, release rhythm 50, longevity 44
- inputs: {"age_days": 616, "days_push": 120, "days_rel": 121, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1526, forks 170 (observed 2026-08-28T04:04:58.395950+00:00)

## What it is
LitterBox is a self-hosted payload-analysis sandbox for red teams that runs static, dynamic, and EDR-based analysis on samples and produces a Detection Score with triggering indicators. It includes an MCP server so LLM agents can drive the analysis pipeline end to end, and can dispatch payloads to an EDR-instrumented Windows VM.

## Use cases
- test if my payload gets detected by EDR before deployment
- run static and dynamic malware analysis on a sample
- check which YARA rules trigger on my binary
- self-host a sandbox to score payload detection risk
- let an LLM agent automate malware analysis via MCP
- dispatch samples to an Elastic Defend or Fibratus VM and collect alerts
- blue team malware triage with detection indicator breakdown

## When to choose
- you are a red team operator validating payloads against modern detection before field use
- you want a self-hosted alternative to online sandboxes for sensitive samples
- you want LLM-driven automated malware analysis via MCP
- you need EDR telemetry (Elastic Defend, Fibratus) correlated with sandbox results

## When to avoid
- you need a general-purpose production malware detonation service at scale
- you lack Windows environments or admin access for EDR integration
- you only need simple antivirus scanning without detection scoring
- your organization prohibits offensive-security tooling

## Facets
- artifact type: application
- maturity: active
- function: security, penetration-testing, vulnerability-scanning, mcp, self-hosted, developer-tools
- domain: security, penetration-testing, developer-tools, self-hosted
- platform: windows, self-hosted, python
- tags: red-team, malware-analysis, sandbox, edr-testing, payload-analysis, yara, detection-scoring, offensive-security, linux, docker

## Member repositories
- BlackSnufkin/LitterBox (main) score 62

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:58.395950+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:31:35.154663+00:00, confidence not recorded.
  - readme: https://github.com/BlackSnufkin/LitterBox (fetched 2026-08-28T04:04:58.395950+00:00, sha 3481f9489a20)
- Data as of 2026-08-30T08:39:29.467469+00:00.