Agent Plugins Marketplace
← All plugins

umbra

v0.5.0

Umbra — autonomous, authorization-gated, multi-agent penetration testing for Claude Code. Recon-first orchestration across a Kali network track and an agent-browser web track; all offensive tooling runs inside a disposable, egress-locked sandbox behind an explicit scope allowlist.

Claude Code2 Skills

By mushhzzLicense: MIT2 GitHub starsUpdated 2 months ago

Directory evidence

Runtimes
Claude Code
Parsed components
2 skill or MCP entries
Source updated
Aug 10, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install umbra for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install umbra@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/mushhzz/umbra

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

umbra/
├── .claude-plugin/plugin.json
├── skills/pentest-orchestration/SKILL.md
└── skills/pentest-reporting/SKILL.md

Included Skills2

pentest-orchestrationskills/pentest-orchestration/SKILL.md

Use when running an authorized penetration-testing engagement — classify the target(s), pick the right execution track, delegate to specialist roles, verify findings, and report. Requires an established scope allowlist; the Kali Docker sandbox for host/network work.

pentest-reportingskills/pentest-reporting/SKILL.md

Use to produce the final engagement report for a penetration test — assembles verified findings into a structured markdown report with severity, evidence, and remediation.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "umbra",
  "version": "0.5.0",
  "description": "Umbra — autonomous, authorization-gated, multi-agent penetration testing for Claude Code. Recon-first orchestration across a Kali network track and an agent-browser web track; all offensive tooling runs inside a disposable, egress-locked sandbox behind an explicit scope allowlist.",
  "author": {
    "name": "mushhzz"
  },
  "homepage": "https://github.com/mushhzz/umbra",
  "repository": "https://github.com/mushhzz/umbra",
  "license": "MIT",
  "keywords": [
    "security",
    "pentest",
    "penetration-testing",
    "offensive-security",
    "sandbox",
    "kali"
  ],
  "agents": [
    "./agents/adviser.md",
    "./agents/assistant.md",
    "./agents/coder.md",
    "./agents/enricher.md",
    "./agents/generator.md",
    "./agents/installer.md",
    "./agents/memorist.md",
    "./agents/orchestrator.md",
    "./agents/pentester.md",
    "./agents/refiner.md",
    "./agents/reflector.md",
    "./agents/reporter.md",
    "./agents/searcher.md",
    "./agents/summarizer.md",
    "./agents/verifier.md"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[umbra on Agent Plugins Marketplace](https://pluginsmp.com/plugins/umbra)