Claude
Skills
Sign in
Back

red-team

Included with Lifetime
$97 forever

Offensive security team skill providing methodology guidance for penetration testing and red team engagements. Invoked when users request penetration testing, reconnaissance, vulnerability analysis, exploitation methodology, social engineering, C2 infrastructure, or engagement reporting. Routes to 11 specialized agents covering the full MITRE ATT&CK kill chain. All engagements require red-lead scope authorization before any other agent. Follows PTES, OSSTMM, and ATT&CK methodology frameworks.

AI Agents

What this skill does


# Red Team Skill

> **Version:** 1.0.0
> **Framework:** Jerry Red-Team
> **Constitutional Compliance:** Jerry Constitution v1.0
> **SSOT Reference:** ADR-PROJ010-001 (Agent Team Architecture), ADR-PROJ010-006 (Authorization & Scope Control)

## Document Audience (Triple-Lens)

This SKILL.md serves multiple audiences:

| Level | Audience | Sections to Focus On |
|-------|----------|---------------------|
| **L0 (Stakeholder)** | Engagement managers, leadership | [Purpose](#purpose), [When to Use This Skill](#when-to-use-this-skill), [Routing Disambiguation](#routing-disambiguation), [Mandatory Authorization](#mandatory-authorization), [Quick Reference](#quick-reference) |
| **L1 (Practitioner)** | Security testers invoking agents | [Available Agents](#available-agents), [Invoking an Agent](#invoking-an-agent), [Orchestration Flow](#orchestration-flow), [Cross-Skill Integration Points](#cross-skill-integration-points) |
| **L2 (Architect)** | Framework designers, governance reviewers | [Authorization Architecture](#authorization-architecture), [Circuit Breaker Integration](#circuit-breaker-integration), [Safety Alignment Compatibility](#safety-alignment-compatibility), [Constitutional Compliance](#constitutional-compliance) |

---

## Purpose

The Red Team skill provides **methodology guidance for authorized penetration testing and red team engagements**. It routes to 11 specialized agents that collectively cover the full MITRE ATT&CK kill chain (14/14 tactics at STRONG coverage level), following established professional methodology frameworks: PTES (Penetration Testing Execution Standard), OSSTMM (Open Source Security Testing Methodology Manual), and NIST SP 800-115 (Technical Guide to Information Security Testing and Assessment).

### Key Capabilities

- **Scope & Authorization Management** -- Formal engagement scoping with Rules of Engagement, target allowlists, and technique authorization
- **Full Kill Chain Coverage** -- 11 agents spanning Reconnaissance through Exfiltration with explicit ATT&CK tactic mapping
- **Non-Linear Workflow** -- Iterative phase cycling that mirrors real engagement dynamics, not rigid sequential execution
- **Distributed Defense Evasion** -- TA0005 techniques embedded in each operational agent's phase-specific tradecraft
- **Cross-Skill Integration** -- 4 purple team integration points with /eng-team for adversarial-collaborative hardening
- **Three-Level Degradation** -- All agents function standalone (AD-010); tools augment evidence quality but do not enable reasoning

### What This Skill Is NOT

This skill provides **methodology guidance**, not autonomous exploitation. It does NOT:

- Execute exploits or payloads autonomously
- Access live systems or networks directly
- Generate weaponized exploit code
- Operate without explicit human authorization
- Replace human judgment for novel discovery or legal decisions

This design follows AD-001 (Methodology-First Design Paradigm): LLMs excel at methodology guidance, structured reasoning, and report generation but fundamentally cannot replace tool execution or human judgment for novel discovery (S-001 Convergence 1, D-002).

---

## When to Use This Skill

Activate when:

- Planning or executing a penetration testing engagement
- Performing reconnaissance or attack surface analysis
- Analyzing vulnerabilities and assessing exploit availability
- Developing exploitation methodology or payload crafting guidance
- Conducting privilege escalation, lateral movement, or persistence operations
- Planning data exfiltration testing within authorized scope
- Setting up C2 infrastructure or engagement tooling
- Conducting social engineering assessments (phishing, pretexting, vishing)
- Generating engagement reports with findings, risk scores, and remediation guidance
- Validating /eng-team defenses through adversarial testing (purple team)

NEVER invoke this skill when:
- Task is building secure software (defensive security) -- Consequence: Offensive methodology applied to defensive engineering produces attack narratives instead of hardened code; STRIDE/DREAD threat modeling and OWASP compliance not loaded; use `/eng-team` instead
- Task is adversarial quality review of deliverables -- Consequence: Penetration testing methodology applied to quality assessment produces engagement reports instead of quality scores; S-014 rubric not available; use `/adversary` instead
- Conducting general security research without an engagement context -- Consequence: Red team agents require authorized scope documents; unscoped security research lacks engagement boundaries and authorization controls; use `/problem-solving` instead
- No active scope document exists and no engagement is being planned -- Consequence: Red team operations without scope authorization violate engagement methodology; agents will halt at scope validation
- Target is outside any authorized engagement boundary -- Consequence: Out-of-scope testing violates rules of engagement; red-lead agent enforces scope authority as a hard gate

See [Routing Disambiguation](#routing-disambiguation) for full exclusion conditions with consequences.

---

## Available Agents

| Agent | Role | ATT&CK Tactics | Model | Output Location |
|-------|------|----------------|-------|-----------------|
| `red-lead` | Engagement Lead & Scope Authority | All (oversight) | opus | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-lead-{topic-slug}.md` |
| `red-recon` | Reconnaissance Specialist | TA0043 Reconnaissance | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-recon-{topic-slug}.md` |
| `red-vuln` | Vulnerability Analyst | Analysis support | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-vuln-{topic-slug}.md` |
| `red-exploit` | Exploitation Specialist | TA0001, TA0002, TA0040 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-exploit-{topic-slug}.md` |
| `red-privesc` | Privilege Escalation Specialist | TA0004, TA0006 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-privesc-{topic-slug}.md` |
| `red-lateral` | Lateral Movement Specialist | TA0008, TA0007 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-lateral-{topic-slug}.md` |
| `red-persist` | Persistence Specialist (RoE-GATED) | TA0003, TA0005 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-persist-{topic-slug}.md` |
| `red-exfil` | Data Exfiltration Specialist (RoE-GATED) | TA0009, TA0010 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-exfil-{topic-slug}.md` |
| `red-reporter` | Engagement Reporter | TA0040 (documentation) | opus | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-reporter-{topic-slug}.md` |
| `red-infra` | Infrastructure & Tooling Specialist | TA0042, TA0011, TA0005 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-infra-{topic-slug}.md` |
| `red-social` | Social Engineering Specialist (RoE-GATED) | TA0043, TA0001 | sonnet | `projects/${JERRY_PROJECT}/engagements/{engagement-id}/red-social-{topic-slug}.md` |

---

## Mandatory Authorization

> **ALL engagements MUST start with red-lead.** No other agent can operate without an active scope document.

This is the foundational security constraint for the /red-team skill. The authorization model ensures that offensive operations are structurally bounded -- out-of-scope actions are architecturally impossible, not merely procedurally discouraged.

### Authorization Flow

```
1. User requests engagement  -->  red-lead creates scope document
2. Scope document defines:
   - engagement_id (RED-NNNN format)
   - authorized_targets (IP ranges, domains, applications)
   - technique_allowlist (ATT&CK technique IDs)
   - time_window (start/end timestamps)
   - exclusion_list (systems/networks explicitly excluded)
   - rules_of_engagement (escalation procedures, communication channels)
   - agent_authorizations (which agents are permitted)
   - evidence_handling (st
Files: 51
Size: 315.5 KB
Complexity: 66/100
Category: AI Agents

Related in AI Agents