How do I install the Redteam skill?

Run npx skillmds add majiayu000/redteam-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Redteam safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Redteam?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Redteam free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Redteam?

majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Redteam by majiayu000 — Agent Skill

Name: Redteam
Rating: 4.2 (5 reviews)
Author: majiayu000

File contents

Red Team Analysis

Conduct an adversarial analysis to find weaknesses, vulnerabilities, and failure modes in a plan, system, or strategy.

Instructions

Think like an attacker. Your job is to break this, find the gaps, and expose what could go wrong. Be thorough and creative in your attacks.

Output Format

Target: [What we're attacking] Objective: [What would "breaking it" look like?]

Target Understanding

Summary of the Plan/System [Brief description of what we're analyzing]

Key Assumptions

[Assumption 1]
[Assumption 2]

Attack Surface Analysis

Entry Points / Vulnerabilities

Vector	Description	Severity
[attack vector]	[how it could be exploited]	Critical/High/Med/Low

Failure Mode Analysis

Technical/Operational Failures

Failure Mode	Trigger	Impact
[what could fail]	[what causes it]	[effect]

Human Failures

Failure Mode	Trigger	Impact
[human error]	[situation]	[consequence]

Adversary Scenarios

If I wanted this to fail, I would...

Scenario 1: [Attack Name]

Attack method: [how they'd do it]
Likelihood of success: [High/Med/Low]
Impact if successful: [consequences]

Scenario 2: [Attack Name]

Attack method: [how]
Likelihood of success: [High/Med/Low]
Impact if successful: [consequences]

Assumption Attacks

Assumption	Attack	What If Wrong?
[assumption]	[challenge to it]	[consequences]

Blind Spot Analysis

What are we not seeing?

[Blind spot 1]
[Blind spot 2]

What are we too optimistic about?

[Over-optimism 1]

Red Team Findings

Critical Vulnerabilities (Must Address)

Vulnerability	Risk	Mitigation
[vulnerability]	[risk level]	[how to fix]

High-Priority Concerns

Concern	Recommendation
[concern]	[recommendation]

Hardening Recommendations

Immediate actions:

[Action 1]
[Action 2]

Ongoing monitoring:

[What to watch]

Bottom Line

[Is this plan/system ready? What must change?]

Guidelines

Be adversarial, not just critical
Think creatively—real attackers don't follow rules
Look for cascading failures
The goal is to make it stronger, not just find flaws

$ARGUMENTS

---name: redteam-2description: Red team adversarial analysis to find weaknesses, vulnerabilities, and failure modes. Use before launches, for security review, or when a plan feels too perfect.--- # Red Team Analysis Conduct an adversarial analysis to find weaknesses, vulnerabilities, and failure modes in a plan, system, or strategy. ## Instructions Think like an attacker. Your job is to break this, find the gaps, and expose what could go wrong. Be thorough and creative in your attacks. ### Output Format **Target**: [What we're attacking] **Objective**: [What would "breaking it" look like?] --- ## Target Understanding **Summary of the Plan/System** [Brief description of what we're analyzing] **Key Assumptions** - [Assumption 1] - [Assumption 2] --- ## Attack Surface Analysis **Entry Points / Vulnerabilities** | Vector | Description | Severity | |--------|-------------|----------| | [attack vector] | [how it could be exploited] | Critical/High/Med/Low | --- ## Failure Mode Analysis ### Technical/Operational Failures | Failure Mode | Trigger | Impact | |--------------|---------|--------| | [what could fail] | [what causes it] | [effect] | ### Human Failures | Failure Mode | Trigger | Impact | |--------------|---------|--------| | [human error] | [situation] | [consequence] | --- ## Adversary Scenarios **If I wanted this to fail, I would...** ### Scenario 1: [Attack Name] - **Attack method**: [how they'd do it] - **Likelihood of success**: [High/Med/Low] - **Impact if successful**: [consequences] ### Scenario 2: [Attack Name] - **Attack method**: [how] - **Likelihood of success**: [High/Med/Low] - **Impact if successful**: [consequences] --- ## Assumption Attacks | Assumption | Attack | What If Wrong? | |------------|--------|----------------| | [assumption] | [challenge to it] | [consequences] | --- ## Blind Spot Analysis **What are we not seeing?** - [Blind spot 1] - [Blind spot 2] **What are we too optimistic about?** - [Over-optimism 1] --- ## Red Team Findings ### Critical Vulnerabilities (Must Address) | Vulnerability | Risk | Mitigation | |---------------|------|-----------| | [vulnerability] | [risk level] | [how to fix] | ### High-Priority Concerns | Concern | Recommendation | |---------|----------------| | [concern] | [recommendation] | --- ## Hardening Recommendations **Immediate actions**: 1. [Action 1] 2. [Action 2] **Ongoing monitoring**: 1. [What to watch] --- **Bottom Line** > [Is this plan/system ready? What must change?] ## Guidelines - Be adversarial, not just critical - Think creatively—real attackers don't follow rules - Look for cascading failures - The goal is to make it stronger, not just find flaws $ARGUMENTS

Frequently asked questions