redteam

Generate failing tests that expose code, architecture, and security weaknesses.

18|3|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/ondrej-svec/heart-of-gold-toolkit --skill redteam-ondrej-svec
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: redteam
Source: https://github.com/ondrej-svec/heart-of-gold-toolkit/tree/main/plugins/marvin/skills/redteam
Command: npx skills add https://github.com/ondrej-svec/heart-of-gold-toolkit --skill redteam-ondrej-svec

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Find weaknesses and expose them with failing tests. You are the adversary — your job is to break things, not fix them.

Core Features & Use Cases

  • Adversarial review to discover vulnerabilities, architectural conformance gaps, and test gaps.
  • Write failing tests that expose weaknesses without modifying production code.
  • Works standalone or in CI pipelines via environment variables and pipelines.

Quick Start

Trigger a red-team validation by generating failing tests that expose weaknesses without touching production code.

Frequently Asked Questions about redteam

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate failing tests that expose code weaknesses without modifying production code?

Adversarial review generates targeted failing tests by reading your source code and writing tests that break on discovered weaknesses, without touching implementation. It exposes vulnerabilities, architectural gaps, and test gaps through failing test output.

What is adversarial code review and how does it find security edge cases?

Adversarial code review treats you as the adversary aiming to break things. It reads source code, generates new failing tests targeting security edge cases and architectural conformance gaps, and reports findings without fixing or modifying the underlying implementation.

Can I run adversarial security testing in a CI pipeline?

Yes, adversarial security testing works in CI pipelines via environment variables. It reads source code, generates failing tests that expose weaknesses, and reports findings through the configured toolset, fitting standalone projects and automated pipeline contexts.

Does architecture conformance checking work without modifying my existing implementation?

Architecture conformance checking generates failing tests that expose structural gaps without modifying production code. It reads your source, detects stubs, validates architectural conformance, and reports weaknesses through targeted test failures rather than implementation changes.

What is the difference between adversarial review and standard code review?

Adversarial review focuses exclusively on breaking code rather than fixing it. It generates targeted failing tests to expose vulnerabilities, architectural conformance gaps, and security edge cases, whereas standard code review typically suggests fixes rather than demonstrating failures.