Re Hw Chip logo

Re Hw Chip

Community
dslsdzc
re-hw-chip

物理层硬件逆向:去封装、裸片分析、探针与 FIB、PCB 电路分析、硬件木马检测。 触发词:芯片逆向、去封装、decapping、PCB、硬件木马、电路分析、裸片、FIB、侧信道、SPA、DPA、故障注入、时钟毛刺、电压毛刺。

Overview

Publisherdslsdzc
Repositoryrev-skills
Skill namere-hw-chip
Stars
191
Forks
35
Bundled files
Instructions only
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by dslsdzc on GitHub. Read the source before you install it.

Installation

Install the Re Hw Chip AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/dslsdzc/rev-skills/tree/main/.claude/skills/re-hw-chip
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/dslsdzc/rev-skills.git /tmp/rev-skills
mkdir -p .claude/skills
cp -r /tmp/rev-skills/.claude/skills/re-hw-chip .claude/skills/re-hw-chip
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Re Hw Chip in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Re Hw Chip on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Re Hw Chip is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

芯片/PCB 硬件逆向

何时使用 / 何时不用

  • 用:物理芯片/板级分析(固件提取失败后的物理层)、芯片解密、硬件木马检测
  • 不用:固件级分析(转 [[re-fw-extract]]);接口提取(转 [[re-hardware-io]]);无线信号(转 [[re-sdr]])

工具准备

显微镜/探针台(观察与接触)

  • 选购指引:体视显微镜(初检)→ 金相显微镜(裸片);探针台按预算分级
  • 验证: 无软件验证——以成像清晰度验收

decapping 设备与耗材(去封装)

  • 化学 decap:发烟硝酸/硫酸 + 加热台(防护:通风橱/护目镜);激光 decap:专用激光器(高成本,外包可选)
  • 验证: 无软件验证——以裸露程度验收

逻辑分析仪(信号提取)

  • 多平台: Saleae 类(配套软件各平台可用)或开源方案(sigrok/PulseView:apt install sigrok-cli pulseview / brew install sigrok-cli pulseview(sigrok 无 PyPI 包))
  • 验证: pulseview --version

热成像(功耗/时序异常,可选)

  • 选购指引:按分辨率与测温范围选型;验证: 成像验收

操作步骤

按顺序执行;全程注意防护与破坏性风险(步骤 1 不可逆)。

  1. 去封装(decapping):

    • 化学法:加热台预加热 → 滴加发烟硝酸溶解环氧 → 清洗(丙酮)→ 显微镜检查
    • 激光法:激光逐层烧蚀(精度高,成本高)
    • 风险控制:通风橱、防酸手套/护目镜、废弃液处理;先练习废片
    • 验收:金属层可见、无过度腐蚀(伤及晶圆)
  2. 裸片分析:

    • 显微成像(金相显微镜/电子显微镜)→ 金属层走线观察
    • ROM/熔丝提取:成像 → 位图还原(金属层/多晶硅层图案 → 二进制)
    • 产出:ROM 位图 → 数据(与 [[re-fw-extract]] 固件对照)
  3. 探针与信号提取:

    • 探针台接触测试点(总线/时钟/数据线)
    • FIB(聚焦离子束):修改互连/暴露内部节点(高成本,外包)
    • 信号嗅探:逻辑分析仪挂总线(时序对照数据手册)
    • 注意:探针负载可能改变信号(见坑 2)
  4. PCB 电路分析:

    • 走线还原(万用表导通/成像 → 网络表)
    • IC 标识识别(丝印 → 型号 → 数据手册 → 引脚功能)
    • JTAG/SWD 引脚定位(测试点/走线特征 → 调试接口枚举)
  5. 硬件木马检测:

    • 冗余逻辑特征(无功能路径的触发器/计数器)
    • 功耗/时序异常(热成像 + 电流曲线对照基线)
    • 触发条件分析(特定输入组合/温度/时间条件)

侧信道与故障注入

功耗侧信道(SPA/DPA)

  • SPA(简单功耗分析):单条或少数功耗曲线直接观察密钥相关操作(乘方运算位数、条件分支的电流差异),适合算法结构已知的场景
  • DPA(差分功耗分析):
    • 采集原理:同一密钥下多次加解密,逐条记录功耗曲线
    • 差分思路:按猜测密钥位分组(如按某轮 S-box 输出某一位为 0/1 分组),组内平均后相减;某猜测下出现显著尖峰,说明该中间值与功耗存在相关性
    • 相关分析:对中间值比特与曲线逐点做相关性计算(CPA 思路),尖峰位置对应操作发生时刻,可反向验证猜测
  • 采集设备(chipwhisperer 类)选购要点:
    • 采样率:不低于目标时钟的数倍(超出奈奎斯特需求),高速时钟下需 GHz 级采样
    • 触发同步:支持外部触发信号(以加解密开始时刻对齐),曲线逐条对齐是差分分析的前提
    • 信噪比:高阻差分探头、短地线、屏蔽可降低噪声;噪声大时靠增加采集条数平均补偿
    • 验证: 无软件验证——以已知密钥采集曲线,确认差分尖峰出现

故障注入(时钟毛刺/电压毛刺)

  • 原理:时钟毛刺在目标指令执行时刻插入过窄的时钟周期,使取指/译码/执行失败,产生跳过分支、破坏中间值等效果;电压毛刺以瞬时欠压实现类似效果
  • 参数扫描流程:
    1. 粗扫:宽度与相位(注入时刻)按大步长铺开,记录有反应的参数点
    2. 细分:对命中区域缩小步长,定位稳定窗口
    3. 复测:同一参数多次注入,确认效果可重放
  • 结果判定:跳过分支(授权校验直接通过)、改返回值(校验函数返回被破坏)、无效果或崩溃(参数越界,回退重扫)
  • 与去封装衔接:裸片探针可接触时钟/总线节点,毛刺注入点与功耗观测点重合,侧信道曲线可与探针波形互证;去封装后注入点选择更多(见上文步骤 1/3)

安全边界

  • 与技能库整体边界一致:仅限授权范围内的自有设备/实验室样品,不涉及具体攻击目标
  • 本节为方法学描述,不提供针对特定对象的操作指引

常见坑与陷阱

  • 波形不同步导致 DPA 无相关性:现象——差分曲线无尖峰、相关值接近零;原因——各条曲线起点未对齐(触发没对准,软件触发延迟抖动);对策——改用硬件触发信号,或事后按固定特征点重对齐
  • 毛刺参数扫不到窗口:现象——全参数范围扫描无任何效果;原因——宽度/相位扫描步长大于命中窗口;对策——先粗扫定位区间再细分步长,必要时增大重复次数
  • 故障注入后设备锁死:现象——注入后设备无响应或进入异常状态;原因——毛刺破坏运行状态或误写存储;对策——实验前备份固件并准备重刷恢复流程,批量注入时按批重启
  • 采集设备带宽不足:现象——高速时钟下曲线失真(边沿变缓、高频细节丢失);原因——采集带宽低于信号频谱需求;对策——按目标时钟选择带宽足够的设备,或降低时钟运行

跨域联合

  • [[re-hardware-io]]:接口提取衔接(JTAG/UART 是软件侧入口)
  • [[re-fw-extract]]:固件侧对照(ROM 提取物与固件 dump 比对)
  • [[re-sdr]]:无线侧(RF 接口)
  • [[re-triage]]:提取物初勘

常见坑与陷阱

  • decap 不可逆:现象——封装破坏后无法恢复;原因——物理破坏;对策——先存档固件([[re-fw-extract]])再做物理操作
  • 探针负载改变信号:现象——挂探针后时序异常;原因——容性负载;对策——高阻探针、记录挂载前后基线
  • FIB 高成本易毁:现象——FIB 修改失败晶圆报废;原因——离子束损伤;对策——先成像规划、外包给专业服务
  • 木马误报:现象——正常冗余逻辑被当木马;原因——厂商设计含测试/修复逻辑;对策——对照数据手册与已知电路模式,低置信度不发布
  • 安全防护缺失:现象——化学 decap 事故;原因——未用通风橱/防护;对策——步骤 1 风险控制强制前置

Frequently asked questions

What does the Re Hw Chip AI skill do?

物理层硬件逆向:去封装、裸片分析、探针与 FIB、PCB 电路分析、硬件木马检测。 触发词:芯片逆向、去封装、decapping、PCB、硬件木马、电路分析、裸片、FIB、侧信道、SPA、DPA、故障注入、时钟毛刺、电压毛刺。

Why use Re Hw Chip on TypingMind?

Because you install it once and use it with any model. Re Hw Chip is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Re Hw Chip in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dslsdzc/rev-skills/tree/main/.claude/skills/re-hw-chip. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Re Hw Chip?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Re Hw Chip?

As many as you like. As long as a model supports skills, you can use Re Hw Chip with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Re Hw Chip AI skill free?

Yes. It is published on GitHub by dslsdzc under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇