ch015-pentest

A read-only penetration-testing workflow that examines source code from an attacker’s point of view. Penetration testing means looking for ways software could be misused or broken.

In plain words
What is it for?
Use it to explore exploit scenarios, document vulnerabilities, create proof-of-concept code, and review the results of live or dry-run checks.
Why use it?
It searches for attack scenarios and chains of weaknesses instead of checking only a fixed list of code patterns. It can produce proof-of-concept code and, when selected, verify findings live without changing the code.

Skill for Claude CodeCodex

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 skills/ch015/code-pentester/pentest
Any agent
npx skills add ch015/code-pentester --skill pentest
Clone the repo
git clone --depth 1 https://github.com/ch015/code-pentester

Made for: Claude Code, Codex.

Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 21,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00035 $0.21019
Opus 5 $0.00017 $0.10509
Sonnet 5 $0.00007 $0.04204
Haiku 4.5 $0.00003 $0.02102

Measured yesterday against content hash 4bc7c55ef032, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ch015-pentest scanned grade B with 2 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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

- "169.254.169.254"

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

TCP 세그먼트에 모아 전송 (curl --parallel 또는 Turbo Intruder의
skills/ch015/offsec/pentest/SKILL.md · 1,570 lines

How it starts

The opening of the file, as written. The whole thing — 1,570 lines — stays where its author put it; the contents beside it link to each section on GitHub.

모의해킹 (Penetration Testing) Skill

대상 프로젝트의 소스코드를 공격자 관점에서 분석하여 시나리오 기반 취약점 탐색, POC 생성, 선택적 라이브 검증을 수행합니다.


서비스 개요

항목 내용
서비스명 모의해킹 (Pentest)
방법론 시나리오 기반 공격 + 방법론 기반 분석
출력물 취약점 상세 + 6-step 영향도 분석 + POC 코드 + 라이브 검증 결과
코드 수정 ❌ 없음 (읽기 전용)

설계 원칙: 방법론 기반 + 공격자 사고

분석 원칙: 방법론, 패턴이 아님

Principles:
  No_Pattern_Lists: |
    "특정 프레임워크 구문, grep 패턴, 시크릿 접두사 목록에 의존하지 않는다.
     이런 목록은 닫힌 집합이며, 목록에 없는 위험을 구조적으로 놓친다."

  Use_Methodology: |
    "행위(무엇이 일어나는가)를 질문하고, AI가 감지된 기술 스택에 맞는
     구체적 코드 패턴을 자율적으로 판단하여 탐색한다."

  Attacker_Mindset: |
    "방어자가 아닌 공격자 관점으로 코드를 읽는다.
     '이 기능이 안전한가'가 아니라 '이 기능을 어떻게 악용할 수 있는가'를 질문한다."

  Representative_Examples: |
    "안티패턴/올바른 패턴은 '대표적 예시'로만 제시.
     분석은 이 예시에 한정되지 않으며 — 동일한 구조적 이슈를 가진
     모든 변형이 탐지되어야 한다."

Phase 구조

Phase 0: Recon          → 공통 정찰 (common/recon.md 참조)
Phase 0.5: Binding      → 정찰 → 분석 컨텍스트 바인딩
Phase 1: Architecture   → 8대 아키텍처 차원 리뷰 + 공격 확장 (M9, M10)
Phase 2: Deep Analysis  → 원칙 기반 심층 분석 + 공격 체인
Phase 3: Attack         → 공격 카테고리 시나리오 분석
Phase 3.5: Creative     → 체크리스트 외 프로젝트 고유 공격 추론
Phase 3.8: Routing Plan → Pentest Routing Plan (시나리오 → Route A~F 배정)
Phase 4: POC            → 검증 가능한 POC 코드 생성
Phase 4.5: Self-Verify  → 분석 결과 자체 검증 (도달 가능성, 보상 제어, 전제조건 분석, 로컬 PoC)
Phase 6.0: Sweep        → 엔드포인트 전수 기본 테스트 (--url 옵션 시, Finding 무관)
Phase 6: Live           → Finding 기반 라이브 검증 (--url 옵션 시)
Phase 5: Report         → 종합 보고서 + 6-step 영향도 분석 + 전제조건 포괄 그룹
Phase 5R: Regulatory    → 규제 영향 참조 (Finding 기반, 해당 시에만)

실행 순서 주의: Phase 5(Report)는 번호와 달리 최종 단계다 — --url 옵션 시 Phase 6.0/6 라이브 검증 결과를 반영한 후 pentest-report.template.md 기반으로 보고서를 생성하고, Phase 5R(규제 영향 참조)을 말미에 첨부한다. Phase 5는 별도 본문 섹션 없이 위 산출 규칙과 템플릿으로 수행한다.

Report Gate 주의 (hooks/report-gate-hook.js): engagement_dir 내부에 파일명에 report/result/summary/backlog가 포함된 .md를 Write/Edit하는 순간 (예: 06_pentest_result.md) report-gate가 발동하여 raw ledger/convergence classification의 분류 완결성을 검증한다. 차단(exit 2)되면 파일명 변경이나 Bash 리다이렉트로 우회하지 말 것 — 누락 산출물의 보완 주체는 raw ledger는 VA Phase 4.7, classification은 OffSec Lead Convergence이므로, blocker 사유를 반환 메시지로 Lead에 보고하고 보완 후 재시도한다.

Read the full file on GitHub · 1,570 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 · 1,570 lines · 35 tokens per session scan B 4bc7c55ef032

Subscribe to this mod's changes

ch015-pentest is a skill published in the GitHub repository ch015/code-pentester (4 stars, last pushed 13d ago), licensed MIT. It adds 35 tokens to every session and 21,019 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

codebeacon

Scan a codebase → AST extraction → knowledge graph → wiki + CLAUDE.md context map. Supports 27 frameworks (Spring Boot, NestJS, Django, FastAPI, Flask, Rails, Express, Fastify, Koa, React, Next.js, Vue, Nuxt, Angular, SvelteKit, Gin, Echo, Fiber, Laravel, Actix-Web, Axum, Tauri, Rocket, Warp, ASP.NET Core, Vapor…

Wandererer/codebeacon · 99 tokens

test-harness

Test codeweave-mcp tools against any project using TestHarness. Use this whenever verifying tool behavior, testing a code change, or running custom assertions — e.g. "test the harness", "run tests against X project", "does semanticsearch work correctly".

semihkayan/codeweave-mcp · 57 tokens

nexus-mapper

Generate a persistent .nexus-map/ knowledge base that lets any AI session instantly understand a codebase's architecture, systems, dependencies, and change hotspots. Use when starting work on an unfamiliar repository, onboarding with AI-assisted context, preparing for a major refactoring initiative, or enabling…

Haaaiawd/Nexus-skills · 118 tokens

nexus-query

Precise, instant code structure queries for active development — answer 'who depends on this interface before I refactor it', 'how many modules break if I change this', 'what is the real impact radius of this feature change', 'which module is the true high-coupling hotspot in this legacy codebase'. Essential before…

Haaaiawd/Nexus-skills · 119 tokens

repomix

Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.

yamadashy/repomix · 58 tokens

knowledge-base

Create and maintain a Markdown knowledge base that any AI agent can read, search, and update. Use when the user wants to start a knowledge base, add or update notes, organize docs/notes for an agent or LLM to consume, build an index of notes, or run a cleanup/maintenance pass on an existing MD knowledge base. Triggers…

wonderwhy-er/DesktopCommanderMCP · 112 tokens