Skip to content
Agentmart
Submit a tool

gpt56-reverse-pentest

GPT-5.6 全栈逆向+渗透融合 Skill(已并入 Code Sentinel)。 覆盖:通用/深度/脱壳/黑盒/JS/APK/Binary Diff 逆向;渗透/API/攻击链; 游戏/卡密/Pwn/IoT/恶意样本/EDR/LLM/供应链/Patch Diff/CTF 全速解题; Kali…

Skill by z91772524-ai

IndexedMIT★ 77
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/z91772524-ai-gpt56-reverse-pentest

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

GPT-5.6 全栈逆向+渗透融合 Skill(已并入 Code Sentinel)。 覆盖:通用/深度/脱壳/黑盒/JS/APK/Binary Diff 逆向;渗透/API/攻击链; 游戏/卡密/Pwn/IoT/恶意样本/EDR/LLM/供应链/Patch Diff/CTF 全速解题; Kali 工具链、证据工作区、Writeup。与 ops_pipeline / reverse_engineering / ctf_toolkit / web_pentest 联动。触发词:逆向、脱壳、APK、JS 逆向、pwn、 卡密、固件、EDR、CTF 全速、binary diff、游戏外挂分析、全栈安全研究。

Use cases: backend, ml, security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/gpt56-reverse-pentest

What's inside

Skill name
gpt56-reverse-pentest
Description
GPT-5.6 全栈逆向+渗透融合 Skill(已并入 Code Sentinel)。 覆盖:通用/深度/脱壳/黑盒/JS/APK/Binary Diff 逆向;渗透/API/攻击链; 游戏/卡密/Pwn/IoT/恶意样本/EDR/LLM/供应链/Patch Diff/CTF 全速解题; Kali 工具链、证据工作区、Writeup。与 ops_pipeline / reverse_engineering / ctf_toolkit / web_pentest 联动。触发词:逆向、脱壳、APK、JS 逆向、pwn、 卡密、固件、EDR、CTF 全速、binary diff、游戏外挂分析、全栈安全研究。
License
MIT
Instructions
209 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (20)

  • SKILL.md
  • ai-security.md · references/
  • api-security.md · references/
  • apk-reverse.md · references/
  • binary-diff.md · references/
  • ctf-speedrun.md · references/
  • edr-bypass.md · references/
  • game-hacking.md · references/
  • iot-firmware.md · references/
  • kali-toolchain.md · references/
  • linux-privesc.md · references/
  • malware-analysis.md · references/
  • reverse-cheatsheet.md · references/
  • software-cracking.md · references/
  • supply-chain.md · references/
  • web-payloads.md · references/
  • web-reverse.md · references/
  • crypto_helper.py · scripts/
  • pwn_template.py · scripts/
  • reverse_tools.py · scripts/

SKILL.md (first lines)

# GPT-5.6 全栈安全研究 · Code Sentinel 融合包

本 Skill 来自 `gpt56-reverse-pentest`,已**融合进 Code Sentinel** 交付树:

| 位置 | 路径 |
|------|------|
| Skill 包 | `$CODE_SENTINEL_HOME/codex-bundle/skills/gpt56-reverse-pentest/` |
| 参考文档 | `$CODE_SENTINEL_HOME/references/gpt56-reverse-pentest/`(16 篇) |
| 辅助脚本 | `$CODE_SENTINEL_HOME/scripts/gpt56_reverse_pentest/` |
| 总编排 | `ops_pipeline` / `ops_router` / `ops_ctf_runner` / `pentest_suite` |

工作根:`CODE_SENTINEL_HOME`(注入后见 `code-sentinel.env`)。

---

## 与 Code Sentinel 主栈的关系

**先本地取证,再方法论。** 禁止编造命令输出。

```bash
# 健康 / 会话包
python "$CODE_SENTINEL_HOME/sentinel.py" doctor
python "$CODE_SENTINEL_HOME/scripts/ops_gpt56.py" session "<任务>" --target <路径> --paste

# 二进制 / 样本
python "$CODE_SENTINEL_HOME/scripts/reverse_engineering.py" <bin> --json
python "$CODE_SENTINEL_HOME/scripts/malware_analysis.py" <sample> --json
python "$CODE_SENTINEL_HOME/scripts/re_surface.py" <bin> --json

# 全深流水线
python "$CODE_SENTINEL_HOME/scripts/ops_pipeline.py" <target> --query "逆向+渗透"
python "$CODE_SENTINEL_HOME/sentinel.py" pipeline <target> --query "..."

# Web / 侦察
python "$CODE_SENTINEL_HOME/scripts/web_pentest.py" <url> --json
python "$CODE_SENTINEL_HOME/scripts/pentest_recon.py" <host> --json

# CTF
python "$CODE_SENTINEL_HOME/scripts/ops_ctf_runner.py" resume .
python "$CODE_SENTINEL_HOME/scripts/ctf_toolkit.py" <challenge>

# 本包辅助脚本
python "$CODE_SENTINEL_HOME/scripts/gpt56_reverse_pentest/reverse_tools.py"
python "$CODE_SENTINEL_HOME/scripts/gpt56_reverse_pentest/crypto_helper.py"
# pwn_template.py 需要 pwntools,按题复制改写
```

路由建议:口语任务先 `ops_framing.py auto`;信号路由 `ops_router` S1–S8;领域方法包 `ops_method_packs`。

---

## 领域导航图

```
                        全栈安全研究 Skill(融合 CS)
                              |
        +---------------------+---------------------+---------------------+
        |                     |                     |                     |
    逆向工程类            安全测试类            专项研究类          交付工程化
        |                     |                     |                     |
  通用/深度/脱壳        渗透/高级渗透        游戏/卡密/Pwn        Kali 工具链
  黑盒/JS/APK           API/浏览器自动化     固件/恶意样本        Case Lab
  Binary Diff           攻击链编排           EDR/LLM/供应链       Journal/Writeup
                        CS: web_pentest      CTF 全速 / Patch Diff  CS: ops_case
                        CS: pentest_recon    CS: malware_analysis   ops_journal
```

---

## 第一部分:逆向工程

### 1.1 通用逆向
文件识别 → 静态反编译 → 字符串/关键函数 → 动态验证 → 算法还原  
工具:IDA / Ghidra / x64dbg / GDB · 本地:`reverse_engineering.py`

### 1.2 深度逆向
CFG、C++/Rust 对象、虚表、异常链、内核驱动

### 1.3 脱壳
UPX/ASPack → ASProtect/Armadillo → Themida/VMProtect → Enigma  
方法:ESP 定律、内存 dump、硬件断点 · 详见 `references/software-cracking.md`

### 1.4 黑盒逆向
I/O 观察、strace/Procmon、抓包、文件行为、差分输入

### 1.5 JS 逆向
XHR 断点、混淆还原、补环境、签名算法 · `references/web-reverse.md`

### 1.6 APK 逆向
apktool/jadx → SO → Frida/JDWP → 重打包 · `references/apk-reverse.md`

### 1.7 IDA / radare2
IDAPython、FLIRT、r2 `aaa/afl/pdf`、r2pipe

### 1.8 Binary Diff
Diaphora/Bindiff、N-day、符号迁移 · `references/binary-diff.md`

---

## 第二部分:安全测试

### 2.1–2.2 渗透 / 高级渗透
PTES 七阶段;域渗透、PTH/PTT、隧道、后渗透  
本地:`pentest_recon` / `web_pentest` / `ops_chain`

### 2.3 API 安全
OWASP API Top 10 · `references/api-security.md`

### 2.4 浏览器自动化
Playwright / Puppeteer / Selenium + Burp

### 2.5 攻击链编排
信息收集 → 初始访问 → 提权 → 凭据 → 横向 → 目标 · `ops_chain.py plan`

---

## 第三部分:专项研究

| 域 | 参考 | CS 联动 |

From z91772524-ai/pojia-next-mac, MIT.

More from z91772524-ai/pojia-next-mac

Signals

Stars
77
Forks
12
Open issues
0
Last commit (this folder)
Sep 28, 2026 (1 month ago)
Last release
Oct 10, 2026 (18 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from z91772524-ai

Cite this page

gpt56-reverse-pentest skill. Agent Mart. https://agentmart.dev/skills/z91772524-ai-gpt56-reverse-pentest (last updated 2026-10-24)