red-team

Generate structured red-team attack scenarios against design documents.

1|1|Updated Dec 30, 2025

Search Tags:#multi-model #consensus #red-team #design-docs #risk-analysis #security-design #attack-scenarios

Ready to run

npx skills add https://github.com/0xHoneyJar/loa-constructs --skill red-team-0xhoneyjar

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: red-team
Source: https://github.com/0xHoneyJar/loa-constructs/tree/main/.claude/skills/red-teaming
Command: npx skills add https://github.com/0xHoneyJar/loa-constructs --skill red-team-0xhoneyjar

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Red Team — Generative Adversarial Security Design helps security and product teams stress-test design documents by generating structured, adversarial attack scenarios and suggesting robust counter-designs.

Core Features & Use Cases

Adversarial scenario generation: produces realistic attack narratives targeting PRDs, SDDs, sprint plans, and specs.
Consensus-driven evaluation: aggregates multi-model assessments into final risk classifications with recommended mitigations.
Workflow integration: integrates with design-review processes and supports inline spec fragments for quick testing.

Quick Start

Supply the target design document or an inline spec and run the red-team workflow to generate attack scenarios against the document.

Frequently Asked Questions about red-team

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

FAQPage Schema

How do I generate adversarial attack scenarios against a design document?▼

Adversarial scenario generation evaluates design documents by producing realistic attack narratives and suggesting robust counter-designs. You supply a target PRD, SDD, sprint plan, or spec to uncover weaknesses through structured red-team attack scenarios.

What is consensus-driven evaluation in multi-model security design?▼

Consensus-driven evaluation aggregates multi-model assessments into final risk classifications. By coordinating across multiple evaluators, the red-team workflow generates recommended mitigations and ensures comprehensive adversarial security analysis of your design specs.

How do I run a risk analysis on an inline spec fragment?▼

Run risk analysis on an inline spec fragment by supplying the fragment to the red-team workflow. It integrates with design-review processes to quickly generate attack scenarios and evaluate security weaknesses without requiring a full document.

Can I use multi-model coordination to uncover weaknesses in a PRD?▼

Yes, multi-model coordination uncovers weaknesses in a PRD by applying the red-team workflow. It evaluates product requirements documents by generating structured attack scenarios and proposing counter-designs through aggregated consensus assessments.

What types of design documents are supported for security red-teaming?▼

Supported documents for security red-teaming include PRDs, SDDs, sprint plans, and specs. The Skill evaluates these targets to generate attack scenarios, classify risks via multi-model consensus, and propose mitigations for your security design.