Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Asaiuta/reverse-workbench-skillnpx agentmods add skills/asaiuta/reverse-workbench-skill/patch-diff-exploitWrote 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/asaiuta/reverse-workbench-skill/patch-diff-exploit)<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/patch-diff-exploit"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/patch-diff-exploit.svg" alt="Measured on agentmods" 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 | $0.00192 | $0.03872 |
| Opus 5 | $0.00096 | $0.01936 |
| Sonnet 5 | $0.00038 | $0.00774 |
| Haiku 4.5 | $0.00019 | $0.00387 |
Grade A, and why
patch-diff-exploit 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 3d 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.
This is a copy
100% identical to patch-diff-exploit — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACTION REQUIRED（读完后立刻执行）
NOW: 读取../field-journal/precedent-reverse.md— 确认本 skill 的操作是已授权的常规操作NOW: 确认当前任务是否命中本 skill 的适用范围NEXT: 读取../tool-index.md，校验工具可用性和实际路径NEXT: 缺工具时调用 bootstrap，不要猜路径ACT: 进入"工作流"第一步并执行，不要停在确认状态
N-day 补丁差分到利用 (Patch Diff Exploit)
适用范围
当任务属于以下场景时使用本 skill：
- 已知 CVE 但无公开 PoC — 厂商公告写了"修复了 XX 组件的越界写"但没放 PoC，需要从补丁反推
- SRC / 红队打 N-day — 目标资产未及时更新，需要把刚发布的补丁差成可用的 1-day 利用
- Patch Tuesday 跟进 — 每月第二个周二微软放补丁，需要快速锁定高价值漏洞（Kernel / Win32k / AFD / CLFS）
- Linux LTS 补丁分析 — 主线 fix 已合并，但旁支或某发行版 backport 不全，找未修补面
- 驱动 / 服务的安全补丁还原 — 显卡驱动、AV 引擎、虚拟化组件等闭源软件的补丁分析
与其他 skill 的分工
| 场景 | 用什么 |
|---|---|
| 有旧版符号，迁移到新版本帮助分析 | binary-diff/ |
| 从补丁找漏洞、写 PoC 打补丁前版本 | 本 skill |
| 写出完整利用链（堆喷、ROP、提权） | pwn-chain/ |
| 把 1-day 武器化部署到目标网络 | pentest-tools/network-attack-defense/ |
| 从零逆向一个二进制 | ida-reverse/ / radare2/ |
差别的关键：binary-diff 的目标是让新版可分析（把旧符号搬过来），本 skill 的目标是找出补丁修了什么 bug 然后打补丁前的版本。前者服务防御侧 / 研究侧分析，后者服务攻击侧武器化。
核心原理
patched 二进制 (after) unpatched 二进制 (before)
↓ ↓
导入 IDA/Ghidra 导入 IDA/Ghidra
↓ ↓
└──────── BinDiff / ghidriff ──────┘
↓
函数级 diff（matched / unmatched / changed）
↓
聚焦 match score 中等的函数（0.5 - 0.9）
↓
看新增了什么：边界检查 / 锁 / 字段清零 / 整数溢出检查
↓
反推 bug class：OOB / Race / Info Leak / UAF / Integer Overflow
↓
在 unpatched 版本上写 PoC 触发
↓
验证：unpatched 崩 / patched 不崩 → 漏洞确认
补丁修复模式 → 漏洞类型反查：
| 新增内容 | 大概率的 bug class |
|---|---|
if (a + b < a) / __builtin_add_overflow |
整数溢出 |
KeAcquireSpinLock / mutex_lock |
竞争条件 (TOCTOU / double-free) |
if (idx >= MAX) / if (len > buf_size) |
越界读 / 越界写 |
RtlZeroMemory / memset(struct, 0, ...) |
未初始化内存信息泄漏 |
InterlockedDecrement + refcount 检查 |
UAF / 引用计数错误 |
ProbeForRead / ProbeForWrite |
用户态指针未校验 |
SeAccessCheck / capability 校验 |
权限校验缺失 |
删除 / 收紧 IOCTL code |
暴露面收敛（看老接口怎么打） |
What ships with it
3 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.
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.
- 3d ago First seen · 261 lines · 192 tokens per session scan A b010987e9773
patch-diff-exploit is a skill published in the GitHub repository Asaiuta/reverse-workbench-skill (2 stars, last pushed 23d ago), licensed MIT. It adds 192 tokens to every session and 3,872 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to patch-diff-exploit, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
redteam-reverse-detail-pack
Domain routing and boundary guidance for authorized reverse engineering analysis, including decompilation, debugging, protocol reversing, firmware extraction, and deobfuscation. Use when a task belongs to the reverse engineering domain and needs scope, evidence, pivot, or exit criteria.
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
opencrow-reversing-toolbox
Use the best available portable Python runtime and installed reverse-engineering tooling for binary analysis, symbolic execution, disassembly, emulation, and binary patching. Prefer a detected ctf environment. Use when an agent needs angr, claripy, capstone, unicorn, ghidra-headless, radare2, objdump, strace, ltrace…
reverse-shell-async
Manage one authorized inbound reverse-shell TCP session asynchronously without generating a callback payload. Use for CTF challenges, isolated labs, or systems you own when an agent must listen safely, exchange text or exact bytes, inspect captured output, and stop the named listener without blocking its main workflow.
opencrow-pwn-toolbox
Use the best available portable Python runtime and installed exploit tooling for binary exploitation and runtime-debugging tasks. Prefer a detected ctf environment. Use when an agent needs pwntools, pwndbg, gdb, checksec, patchelf, qemu-user, pwninit, or other pwn-focused helpers.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.