Borrowing it
Nothing to install: this file belongs to zhaji2333/CkSKILLS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zhaji2333/CkSKILLS/main/.agents/skills/windows-reverse-engineering/SKILL.mdgit clone --depth 1 https://github.com/zhaji2333/CkSKILLSWrote 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/zhaji2333/ckskills/windows-reverse-engineering)<a href="https://agentmods.dev/skills/zhaji2333/ckskills/windows-reverse-engineering"><img src="https://agentmods.dev/badge/skills/zhaji2333/ckskills/windows-reverse-engineering/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/zhaji2333/ckskills/windows-reverse-engineering"><img src="https://agentmods.dev/badge/skills/zhaji2333/ckskills/windows-reverse-engineering.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 243 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high YARA Match · line 351 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
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 | $0.00129 | $0.04385 |
| Opus 5.5 | $0.00052 | $0.01754 |
| Sonnet 5.5 | $0.00026 | $0.00877 |
| Haiku 4.5 | $0.00013 | $0.00439 |
Grade A, and why
windows-reverse-engineering 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 — 399 lines — stays where its author put it; the contents beside it link to each section on GitHub.
windows-reverse-engineering — Windows 逆向与二进制漏洞专项深度挖掘
何时调用（触发条件）
- 拿到 Windows PE 文件（EXE/DLL/SYS）需要逆向分析
- 目标为 Windows 服务/守护进程，需挖掘内存破坏类漏洞
- 程序处理网络/文件/IPC 输入，存在溢出/命令执行面
- 需要 .NET 程序反编译（dnSpy/ILSpy）
- 驱动/内核组件漏洞挖掘（IOCTL、Pool 溢出）
- 协议逆向、加密算法还原
- 需要绕过反调试/反虚拟机/反分析
- 需要构造 PoC/exploit 验证漏洞可利用性
一、漏洞类型全景
| 类型 | 危险函数/场景 | 挖掘要点 |
|---|---|---|
| 缓冲区溢出 | strcpy/strcat/sprintf/gets/memcpy/wcscpy | 栈溢出、堆溢出、off-by-one、整型溢出 |
| 远程命令执行 | system/CreateProcess/ShellExecute/WinExec | 命令拼接、UNC路径、COM接口滥用 |
| 权限提升 | 服务路径未引用/UAC绕过/令牌滥用/弱权限 | Unquoted Service Path、DLL劫持、令牌窃取 |
| 信息泄露 | 硬编码凭证/调试输出/内存残留/配置文件 | 字符串扫描、资源段、内存dump |
| 拒绝服务 | 未校验长度/空指针/除零/死循环/资源耗尽 | 输入长度异常、空对象解引用 |
二、工具链
静态分析
反汇编：IDA Pro / Ghidra / Binary Ninja / Radare2
反编译：Hex-Rays / Ghidra Decompiler / RetDec
.NET： dnSpy / ILSpy / dotPeek
字符串：Strings / FLOSS / BinText
结构： PEview / CFF Explorer / Detect It Easy (DIE)
扫描： cppcheck / FlawFinder / Semgrep（带源码时）
YARA： 规则匹配已知漏洞模式/恶意特征
动态分析
调试器：x64dbg/x32dbg / WinDbg / OllyDbg
.NET： dnSpy 动态调试
Hook： Frida / API Monitor / Detours
内存： Cheat Engine / Process Hacker
网络： Wireshark / mitmproxy / socket replay
模糊测试：AFL++ / WinAFL / boofuzz（协议）/ honggfuzz
流量重放：scapy / 自定义 Python socket
漏洞利用
框架： pwntools / mona.py (Immunity) / ROPgadget
Shellcode：msfvenom / shellcodecs / 自写
Gadget： ROPgadget / ropper / rp++
计算： !py mona pattern_create / pattern_offset
三、静态分析要点
1. 信息收集先行
文件类型：DIE / TrID 识别编译器/语言/壳
PE结构： 检查 ASLR/DEP/CFG/SafeSEH/SEHOP 保护标志
导入表： 关注危险 API（见下表）
字符串： 提取 URL/IP/路径/密钥/SQL/错误信息
资源段： 嵌入配置/证书/PE/脚本
2. 危险 API 速查表
| 类别 | 危险 API | 风险 |
|---|---|---|
| 字符串 | strcpy/strcat/sprintf/vsprintf/gets | 栈溢出 |
| 宽字符 | wcscpy/wcscat/swprintf | 栈溢出 |
| 内存 | memcpy/RtlCopyMemory/memmove | 长度可控溢出 |
| 格式化 | printf/sprintf/fprintf/wsprintf | 格式化字符串 |
| 命令 | system/CreateProcess/ShellExecute/WinExec | 命令注入 |
| 文件 | fopen/CreateFile/WriteFile | 路径穿越/任意写 |
| 网络 | recv/WSARecv/ReadFile(pipe) | 网络输入面 |
| 注册表 | RegSetValue/RegCreateKey | 持久化/配置篡改 |
| 加载 | LoadLibrary/GetProcAddress | DLL劫持/注入 |
| 内存 | VirtualAlloc/WriteProcessMemory | 注入面 |
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 First seen · 399 lines · 129 tokens per session scan A ebbc038dc136
windows-reverse-engineering is a skill published in the GitHub repository zhaji2333/CkSKILLS (126 stars, last pushed 1mo ago), licensed MIT. It adds 129 tokens to every session and 4,385 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via listagents and chatwithagent, emphasizing that the plan is executed by the requester, not by the consulted Agent.
gpt-image-2
A skill for generating or editing images with GPT Image 2 across local, host-provided, or advisory setups.
motion-showreel
A code-based workflow for making short videos built from animated graphics, text, logos, or interface elements. It produces MP4 video and editable source code rather than filming or editing existing footage.
new
Create a new project to start development quickly.
oss-upload
Upload local files to Tencent COS (oss.1024code.com CDN) using coscli. Use when user wants to upload a file to CDN/OSS, or deploy static assets.
officecli-word-form
Use this skill to create fillable Word forms (.docx) with real Content Controls (SDT) + legacy FormField checkboxes + MERGEFIELD mail-merge placeholders + document protection. Trigger on: 'fillable form', 'form fields', 'content controls', 'SDT', 'word form', 'fill in', 'only editable fields', 'protect document'…