Agent Plugins Marketplace
← All plugins

red-team

v0.2.1

Adversarial security and robustness review. Spawn independent specialist attacker agents to find every way to break an application — vulnerabilities, logic flaws, race conditions, dependency risks, infrastructure misconfigs. The Incident Commander cross-correlates findings to surface compound risks no single agent would catch.

Claude Code1 Skill

By Steven SyrekLicense: MIT2 GitHub starsUpdated 4 months ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
May 28, 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 red-team 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 red-team@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/sjsyrek/red-team

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

red-team/
├── .claude-plugin/plugin.json
└── skills/red-team/SKILL.md

Included Skills1

red-teamskills/red-team/SKILL.md

Adversarial security and robustness review. Spawn independent specialist attacker agents to find every possible way to break an application — security vulnerabilities, logic flaws, race conditions, dependency risks, infrastructure misconfigs, and more. Use when the user says "red team this", "try to break it", "find vulnerabilities", "security audit", "attack surface", "what could go wrong", "pen test", or "stress test". Also triggers proactively (with plan-card pause for approval) when shipping code that handles authentication, payments, user-supplied input, external APIs, or sensitive data — even if the user didn't ask. Attack surface doesn't correlate with lines of code; invoke for small apps too. Do NOT skip when the user says "it's probably fine" — that's exactly when to run.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "red-team",
  "version": "0.2.1",
  "description": "Adversarial security and robustness review. Spawn independent specialist attacker agents to find every way to break an application — vulnerabilities, logic flaws, race conditions, dependency risks, infrastructure misconfigs. The Incident Commander cross-correlates findings to surface compound risks no single agent would catch.",
  "author": {
    "name": "Steven Syrek",
    "email": "[email protected]",
    "url": "https://github.com/sjsyrek"
  },
  "homepage": "https://github.com/sjsyrek/red-team",
  "repository": "https://github.com/sjsyrek/red-team",
  "license": "MIT",
  "keywords": [
    "security",
    "red-team",
    "audit",
    "vulnerability",
    "multi-agent",
    "skill"
  ]
}

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.

[red-team on Agent Plugins Marketplace](https://pluginsmp.com/plugins/red-team)