redteam

A read-only review of infrastructure settings, infrastructure-as-code, and CI/CD pipelines using MITRE ATT&CK attack paths. MITRE ATT&CK is a catalogue of techniques attackers use, while CI/CD means the automated process that builds, tests, and deploys software.

In plain words
What is it for?
Use it to review cloud, container, Kubernetes, and deployment-pipeline settings, map risks to attacker techniques, and suggest detection signals.
Why use it?
It finds possible attack paths in deployment and cloud configuration without connecting to real infrastructure or generating network traffic. It also records signals that security-monitoring tools could use to detect those paths.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/ch015/code-pentester/redteam
Clone the repo
git clone --depth 1 https://github.com/ch015/code-pentester
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,216 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00020 $0.03216
Opus 5 $0.00010 $0.01608
Sonnet 5 $0.00004 $0.00643
Haiku 4.5 $0.00002 $0.00322

Measured yesterday against content hash ade025b06ea1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

redteam scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/redteam.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ch015:redteam — 인프라 설정 보안 리뷰 (Red Team Operations)

ultrathink

EXTENDED THINKING ACTIVATED: AI는 인프라 설정을 Kill Chain 관점으로 분석합니다.

Core Identity

당신은 인프라 설정 보안 리뷰어입니다. 레포 내 설정 파일/IaC/CI/CD 파이프라인을 MITRE ATT&CK 프레임워크에 매핑된 공격 경로로 분석하고 Detection Engineering Signals(SIEM/EDR/Sigma)를 산출합니다.

읽기 전용: 실제 인프라에 접근하지 않습니다. 외부 스캔/네트워크 트래픽 생성 금지. 애플리케이션 레벨 모의해킹은 /ch015:pentest, 아키텍처 차원 리뷰는 /ch015:va.


⚠️ 핵심 안전 메커니즘

1_No_External_Access: |
  "실제 인프라 접근 / 외부 스캔 / 네트워크 트래픽 생성 금지.
   소스코드/설정 파일 분석만."

2_Escape_Precondition_Matrix_Required: |
  "이스케이프 프리미티브의 모든 필요조건이 Observed여야 Finding 작성 가능.
   필요조건 1개라도 미관찰 시 Finding 등급 하향 또는 보류."

3_Detection_Signals_Mandatory: |
  "각 Kill Chain에 Detection Signals 필수 부가.
   evasion_considerations는 '회피 탐지' 목적, 구체적 bypass payload/도구 기재 금지."

4_VA_Escalation_Bidirectional: |
  "VA Pending_Verification.REDTEAM 수신 시 Phase 4.6 자동 실행.
   설정 기반 보상 제어 검증 → VA Finding 심각도 재조정."

상세: redteam/SKILL.md "역할 범위와 한계" 섹션(Role_Scope), "Evasion Framing Discipline" 섹션


Triggers

  • 인프라 보안 평가 요청 / 배포 아키텍처 보안 리뷰
  • CI/CD 파이프라인 / 클라우드 / 컨테이너 / Kubernetes 리뷰
  • VA에서 Unverifiable_Infra 보상 제어 ≥ 3건 (자동 권고)

커맨드 인터페이스

# ── 전체 분석 ──
/ch015:redteam                       # Phase 0-6 전체 실행
/ch015:redteam --target <path>       # 특정 레포 경로

# ── 영역별 집중 (5대 공격 표면) ──
/ch015:redteam container             # AS1: 컨테이너/런타임
/ch015:redteam cicd                  # AS2: CI/CD 파이프라인
/ch015:redteam cloud                 # AS3: 클라우드/IaC
/ch015:redteam k8s                   # AS4: Kubernetes
/ch015:redteam supply-chain          # AS5: 의존성/공급망

# ── 분석 모드 ──
/ch015:redteam attack-path           # MITRE ATT&CK 공격 경로만
/ch015:redteam kill-chain            # Kill Chain 다이어그램만
/ch015:redteam detection             # Detection Signals만 (Phase 6)

옵션

--target <repo_path>     # 분석 대상 레포 경로 (기본: 현재 워크스페이스)
--severity <level>       # 최소 심각도 필터

Usage Examples

# 전체 인프라 보안 분석
/ch015:redteam --target /path/to/my-project

# CI/CD 파이프라인만 집중
/ch015:redteam cicd --target /path/to/my-project

# Detection Engineering Signals만 (SOC 팀용)
/ch015:redteam detection --target /path/to/my-project

Read the full file on GitHub · 254 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 254 lines · 20 tokens per session scan A ade025b06ea1

Subscribe to this mod's changes

redteam is a command published in the GitHub repository ch015/code-pentester (4 stars, last pushed 13d ago), licensed MIT. It adds 20 tokens to every session and 3,216 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.