hack

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: hack
description: >-
  Entry P0 primary router for HackSkills. Use when the task involves web
  application testing, API security assessment, recon, vulnerability triage,
  exploit path planning, or choosing the right next category skill before any
  deep topic skill.
---

# HACKING SKILLS / HackSkills

## Overview

This is a top-level routing skill for **bug bounty, web security, API security, and authorized penetration testing**.

Its core role is not to replace all specialized techniques, but to help the agent:

1. First determine the testing phase (Recon / Validation / Privilege Escalation / Chain building)
2. Then select the correct vulnerability category
3. Avoid relying only on baseline model memory; prefer structured methodology
4. Prioritize boundary conditions AI often misses but that matter in real engagements

## Trust Model

- This knowledge base emphasizes content safety and auditability.
- Use this only within **authorized targets**, **legitimate research**, **defensive validation**, and **bug-bounty-approved rules**.
- Do not use these techniques for unauthorized attacks.

## When to Use This Skill

Use this skill first in the following scenarios:

- You just received a new bug bounty target and do not know where to start
- You need to decide whether to load XSS / SQLi / SSRF / IDOR / JWT / API tracks first
- You want the agent to perform Web/API security testing with a more stable methodology
- You need to route scattered findings to the right attack surface
- You want AI to miss fewer critical test points in security work

## Operating Model

### Step 1: Start with Recon and context validation

Collect first:

- Target type: classic web, REST API, mobile backend, admin panel, payment flow, file upload, GraphQL
- Identity and permission model: anonymous, regular user, admin, multi-tenant
- Input locations: URL, query parameters, JSON, headers, cookies, filenames, imported files, templates, reflection points
- Output locations: HTML, attributes, JS, PDF, email, logs, background tasks, mobile endpoints

### Step 2: Route by observed behavior

| Signal | Priority direction |
|---|---|
| Input reflects into HTML / JS | XSS / SSTI |
| Server actively fetches URL / hostname | SSRF |
| Accepts XML / Office / SVG | XXE |
| Path, filename, or download endpoint is controllable | Path Traversal / LFI |
| Many object IDs appear in APIs | IDOR / BOLA / BFLA |
| Login, reset password, 2FA, sessions | Auth Bypass / JWT / OAuth |
| Multi-step transactions, coupons, pricing, inventory | Business Logic |
| MongoDB / JSON query syntax exposure | NoSQL Injection |
| CLI tools, image processing, importers | Command Injection |
| HTTP parsing anomalies / front-back framing mismatch | Request Smuggling |
| Node.js JSON handling / controllable `__proto__` | Prototype Pollution |
| PHP weak comparison / 0e hash / loose conditions | Type Juggling |
| Repeated parameter names / WAF-app parsing mismatch | HTTP Parameter Pollution |
| One-time operations (coupon/inventory/reset) | Race Condition |
| XML/XSLT template processing | XSLT Injection |
| Accessible .git/.svn/.env paths | Insecure SCM |
| CSV/Excel export features | CSV Formula Injection |
| WebSocket protocol upgrades | WebSocket Security |
| Internal package names / supply-chain inventory | Dependency Confusion |

### Step 3: Use the most likely-hit testing order

1. Recon / Methodology
2. API Security / Auth / IDOR
3. XSS / SQLi / SSRF / SSTI / XXE
4. Business Logic / Race Condition
5. Chained exploits and privilege-escalation paths

## Core Skill Map

If you have the full repository, prioritize using these topic documents together:

- [Recon and Methodology](../recon-and-methodology/SKILL.md)
- [XSS Cross Site Scripting](../xss-cross-site-scripting/SKILL.md)
- [SQLi SQL Injection](../sqli-sql-injection/SKILL.md)
- [SSRF Server Side Request Forgery](../ssrf-server-side-request-forgery/SKILL.md)
- [XXE XML External Entity](../xxe-xml-external-entity/SKILL.md)
- [SSTI