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.
npx skills add ch015/code-pentester --skill redteamgit clone --depth 1 https://github.com/ch015/code-pentesterWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ch015/code-pentester/redteam)<a href="https://agentmods.dev/skills/ch015/code-pentester/redteam"><img src="https://agentmods.dev/badge/skills/ch015/code-pentester/redteam/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ch015/code-pentester/redteam"><img src="https://agentmods.dev/badge/skills/ch015/code-pentester/redteam.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00041 | $0.02178 |
| Opus 5.5 | $0.00016 | $0.00871 |
| Sonnet 5.5 | $0.00008 | $0.00436 |
| Haiku 4.5 | $0.00004 | $0.00218 |
Grade A, and why
ch015-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 1mo ago.
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.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
인프라 설정 보안 리뷰 (Red Team Operations) Skill
인프라/네트워크/배포 레벨의 설정 파일과 IaC를 공격자 관점에서 분석하여 MITRE ATT&CK 프레임워크에 매핑된 공격 경로를 식별합니다.
서비스 개요
| 항목 | 내용 |
|---|---|
| 서비스명 | 인프라 설정 보안 리뷰 (Red Team) |
| 방법론 | MITRE ATT&CK 매핑 + Kill Chain 관점 설정 분석 |
| 출력물 | 인프라 공격 표면 맵 + Kill Chain + 6-step 영향도 분석 + 수정 가이드 |
| 코드 수정 | ❌ 없음 (읽기 전용) |
| 외부 스캔 | ❌ 없음 (소스코드/설정 분석 기반) |
| 실제 인프라 접근 | ❌ 없음 (레포 내 파일만 분석) |
역할 범위와 한계
Role_Scope:
정의: |
이 스킬은 "인프라 설정 보안 리뷰(Infrastructure Configuration Security Review)"이다.
실제 인프라에 접근하거나 네트워크 트래픽을 생성하지 않으며,
레포 내 설정 파일/IaC/CI/CD 파이프라인을 공격자 관점(Kill Chain)으로 분석한다.
수행_범위:
- "Dockerfile, docker-compose 등 컨테이너 설정 보안 분석"
- "GitHub Actions, GitLab CI 등 CI/CD 파이프라인 보안 분석"
- "Terraform, CloudFormation 등 IaC 보안 분석"
- "Kubernetes manifest, Helm chart 보안 분석"
- "시크릿 관리 아키텍처 분석 (Vault, SSM, SA binding 등)"
- "코드 내 인프라 클라이언트 호출에서 아키텍처 추론"
- "MITRE ATT&CK Kill Chain 관점 공격 경로 도출"
수행_불가:
- "실제 인프라(클라우드, 서버, 네트워크)에 접근 또는 스캔"
- "실행 중인 서비스에 HTTP 요청 또는 네트워크 패킷 전송"
- "운영 환경의 실시간 설정 값 확인"
- "실제 시크릿 유출 테스트 또는 크레덴셜 검증"
Pentest_차이:
설명: |
- Pentest: 실제 HTTP 요청으로 취약점을 라이브 검증 → FP 직접 제거
- Red Team: 설정 파일을 분석하여 인프라 수준 보상 제어를 확인 → FP 간접 제거
사용_시점: |
VA에서 Unverifiable_Infra로 분류된 보상 제어를 설정 파일에서 검증할 때.
Pentest로 검증할 수 없는 인프라 수준 설정(컨테이너 격리, CI/CD 시크릿 보호 등)이 대상.
FP_감소_기여:
직접: "설정에서 확인 가능한 보상 제어 검증 → Effective/Ineffective 판정"
간접: "Kill Chain 분석으로 복합 공격 경로 식별 → 숨겨진 True Positive 발견"
한계: "레포에 없는 설정(운영 환경 전용)은 검증 불가 → INCONCLUSIVE"
설계 원칙: 방법론 기반 + 공격 경로 중심
분석 원칙: 방법론, 패턴이 아님
Principles:
No_Pattern_Lists: |
"특정 클라우드 서비스 문법, 설정 키, Dockerfile 명령어 목록에 의존하지 않는다.
이런 목록은 닫힌 집합이며, 목록에 없는 위험을 구조적으로 놓친다."
Use_Methodology: |
"행위(무엇이 일어나는가)를 질문하고, AI가 감지된 인프라 스택에 맞는
구체적 설정 패턴을 자율적으로 판단하여 탐색한다."
Kill_Chain_Thinking: |
"개별 설정 결함이 아닌 공격 경로(Kill Chain) 관점으로 분석.
'이 설정이 안전한가'가 아니라 '이 설정을 활용해 어디까지 도달할 수 있는가'를 질문."
Representative_Examples: |
"안티패턴/올바른 패턴은 '대표적 예시'로만 제시.
분석은 이 예시에 한정되지 않으며 — 동일한 구조적 이슈를 가진
모든 변형이 탐지되어야 한다."
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/attack-paths.md 2.3 KB
- references/attack-surface.md 6.6 KB
- references/detection-signals.md 3.0 KB
- references/exploit-deep-analysis.md 1.4 KB
- references/finding-structure.md 2.3 KB
- references/infrastructure-recon.md 4.1 KB
- references/regulatory.md 1.2 KB
- references/self-verification.md 1.6 KB
- references/va-escalation.md 5.8 KB
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.
- 1mo ago Changed · -596 lines scan C → A 4a3382683e28
- 1mo ago First seen · 754 lines · 41 tokens per session scan C 8b90d5dfb133
ch015-redteam is a skill published in the GitHub repository ch015/code-pentester (4 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 2,178 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
ai-code-generation-guardrails
Use when reviewing AI-generated code before merge or execution: plan AST/security checks, isolated behavior tests and evidence, with language-specific coverage limits.
windows-compat
Audit and harden this Rust repo (code-graph-mcp) for Windows correctness: path-spelling drift between producers, the 32,767-char command-line cap, index-key mismatches, and path predicates that assume one ecosystem's layout. Use whenever touching code that builds, compares, prints, or stores a filesystem path; that…
index
Diagnose and fix code-graph index issues. Use when: search returns unexpected/empty results, or after major codebase restructuring. Covers the health check and both rebuild paths from the CLI.
explore
Understand code structure with the AST index before reading files one by one — when starting work in unfamiliar code, exploring a module before a change, or finding which file to edit. An overview lists a directory's symbols and their callers in one call.
setup-agent-guard
Diagnose, install, and verify Agent Guard's plugin-local binary, jq and gitleaks dependencies, the active host integration, and live hook protection. Use when Agent Guard reports degraded protection, a SessionStart warning asks for setup, plugin hooks fail or appear bypassed, or a user asks to finish or repair Agent…
setup-shell
Install or refresh Agent Guard's plugin-local shell integration. Use when the user explicitly asks to enable or update shell command masking, or when a shell-integration warning directs them to rerun setup-shell.