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/SeaOf0/dsh-redteam-modelnpx agentmods add skills/seaof0/dsh-redteam-model/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/seaof0/dsh-redteam-model/patch-diff-exploit)<a href="https://agentmods.dev/skills/seaof0/dsh-redteam-model/patch-diff-exploit"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/patch-diff-exploit/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/seaof0/dsh-redteam-model/patch-diff-exploit"><img src="https://agentmods.dev/badge/skills/seaof0/dsh-redteam-model/patch-diff-exploit.svg" alt="Reviewed on agentmods" width="80" 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 5.5 | $0.00077 | $0.01549 |
| Sonnet 5.5 | $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 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.
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.
- 1mo ago First seen · 261 lines · 192 tokens per session scan A b010987e9773
patch-diff-exploit is a skill published in the GitHub repository SeaOf0/dsh-redteam-model (747 stars, last pushed 10d ago), licensed MIT. It adds 192 tokens to every session and 3,872 once invoked, about $0.0008 per session on Opus 5.5. 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
novel-reviewer
A review and editing workflow for existing novel chapters. It checks story logic, timelines, character states, unresolved clues, world rules, and writing style.
video-recap
A workflow that turns a supplied video into a Chinese narrated recap by combining video understanding, story planning, editing, voiceover, and final assembly.
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.
review-chapter
A six-part review of a manuscript chapter. It compares the chapter with the outline and reports quality, coverage, review status, and problems supported by evidence from the text.
linglu-discipline
A set of 16 operating rules for an AI coding agent, including when to read or write long-term memory and how to report completed actions. It is designed to work with the Lingshu memory service through an MCP connection.
local-search
A local search component that finds web results using installed command-line tools and page parsers. It supports general web search and extra sources for areas such as Chinese pages, news, code questions, academic work, and reference material.