Reverse Skill is a routing package for AI coding agents that selects appropriate reverse-engineering, penetration-testing, and security-research methods and tools for a given target. It is used for tasks involving APKs, binaries, frontend JavaScript, packet captures, CTF challenges, and authorized penetration testing. Its catalogue add-ons provide the skills and instructions that guide these workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zhaoxuya520/reverse-skill --skill malware-analysisgit clone --depth 1 https://github.com/zhaoxuya520/reverse-skillWrote 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/zhaoxuya520/reverse-skill/malware-analysis)<a href="https://agentmods.dev/skills/zhaoxuya520/reverse-skill/malware-analysis"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/malware-analysis.svg" alt="Measured on agentmods" height="20"></a>- Socket pass
- Snyk warn
- NVIDIA SkillSpector pass
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 | $0.00036 | $0.04452 |
| Opus 5 | $0.00018 | $0.02226 |
| Sonnet 5 | $0.00007 | $0.00890 |
| Haiku 4.5 | $0.00004 | $0.00445 |
Grade A, and why
malware-analysis 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- malware-analysis — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Malware Analysis
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
YARA / Sigma / 沙箱 / IOC 提取 / 反反分析 静态 + 动态 + 行为三合一
适用场景
- 恶意软件样本分析(PE/ELF/Mach-O/APK/脚本)
- YARA 规则编写与验证
- Sigma 行为检测规则生成
- 沙箱自动化分析编排
- IOC 提取与威胁情报
- 反分析技术检测与绕过
六阶段分析流程
Phase 1: 初步分诊
# 快速静态检测
file sample.exe # 文件类型
strings sample.exe | grep -i "http\|cmd\|powershell\|base64" # 快速 IOCs
rabin2 -zz sample.exe # 字符串提取 + 交叉引用
floss sample.exe # 去混淆字符串提取(FireEye)
# PE 头部分析
pecheck sample.exe # PE 结构验证
pescan sample.exe # 异常检测(节表、入口点)
diec sample.exe # Detect It Easy(壳/编译器识别)
# Hash 查询
sha256sum sample.exe
# → VirusTotal / MalwareBazaar / Triage 查询
Triage MUST 清单(Issue #65):
□ 文件类型:EXE / DLL / SYS / .NET / 脚本(bat|ps1|vba) / 其他
□ 架构 x86/x64/ARM;查壳(DIE 等)与编译语言线索
□ DLL/SYS:导入表与导出表并列检查(见 Phase 2 硬门)
□ .NET:无传统 IAT → 走 dnSpy/IL/元数据等价锚点(见 Phase 2)
□ 脚本/宏/DLL 专项 P0:见 nonpe-format-cookbook U–AV(E-batch-deobf / E-ps-decode / E-vba-pcode / E-dll-*)
Phase 1b: 脱壳与 IAT 处理(有壳时 · Issue #65)
□ 无壳 / .NET → 跳到 Phase 2
□ 有壳:尝试脱壳(授权隔离环境)→ 尝试修复 IAT
- x86:ImportREC(或等价);x64:Scylla(或等价)。禁止 64 位死磕 ImportREC
□ 【IAT 修复铁律】优先自动/半自动修复;若工具报错或修复后无法运行:
- 立即终止继续静态 IAT 修复
- MUST 记录 E-iat-repair-fail(命令、工具、现象)
- 转入 Phase 3 动态:API 断点(如 bp CreateFile)/ 硬件断点 / 内存搜索抓取导入
- 这不算跳过导入表:路径已尝试并记 Evidence
□ 【补丁 6】脱壳+修 IAT 后闪退/蓝屏(疑 CRC/大小自校验):
- 放弃继续静态修文件;记 E-self-check-crash 或并入 E-iat-repair-fail
- 转 Phase 3:对 CreateFile / GetFileSize / 哈希相关 API 下断
□ 用户指令可行性(§0.5):加壳时用户抢跑「先别脱壳先看导入表」→ 说明阻塞 + 请确认;强制则记 quality=unreadable/packed,禁止冒充完成有意义 IAT
□ 用户要求重做「IAT 修复 / 导入表检查」:MUST 重做被点名步骤(或经确认的前提协商结果),禁止换无关步骤冒充
Phase 2: 静态分析
反汇编/反编译:
□ IDA Pro / Ghidra: 深度反编译
□ radare2: CLI 快速分析
□ x64dbg: Windows GUI 调试器
重点分析区域:
□ 入口点(Entry Point)→ 初始化逻辑
□ 导入表 → API 用途推断(CreateRemoteThread=注入, CryptEncrypt=勒索)
**MUST(硬门)**:执行 rabin2 -i / IDA imports / pecheck 等价命令,将导入表分类摘要写入 Evidence(E-imports)后才能进入 Phase 3(除非已记 E-iat-repair-fail 并走动态旁路,见 Phase 1b)
分类至少覆盖:网络 / 文件 / 加密 / 进程注入 / 注册表 / 其他可疑 API
解析失败或表为空:仍 MUST 记录失败输出,禁止静默跳过
**DLL/SYS**:MUST 并列记录导出表 Evidence(E-exports,`rabin2 -E` 或等价)
**.NET**:无传统 IAT 时 MUST 用 dnSpy/IL/元数据/程序集引用与敏感 API 摘要作为等价锚点,写入 E-imports / E-triage-imports 语义槽
**干净导入表**:仅基础 DLL、几乎无业务 API → MUST 注明动态加载嫌疑(LoadLibrary/GetProcAddress),SHOULD 转入 Phase 3 抓内存 API;若见哈希解析特征 → E-api-hash(补丁 N)
**宽字符串(T)**:ASCII strings 无 IOC 时 MUST 再试 UTF-16(strings -el / IDA unicode)
**签名(F)**:有签名仍 MUST SigCheck;伪造/吊销不降威胁等级
用户要求「重做导入表检查」:MUST 重做本项(阻塞时先走可行性门闩协商),禁止改换其他步骤冒充完成
**高危 API 组合(补丁 8)**:表过长时优先输出恶意组合簇(如 FindWindow+WriteProcessMemory+CreateRemoteThread),过滤纯系统基础调用噪声
□ 资源段 → 嵌入 Payload(.rsrc 节)
□ 字符串表 → URL/C2/文件路径/Base64 blob
□ TLS 回调 → 调试器启动前执行
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.
- 4d ago First seen · 304 lines · 36 tokens per session scan A 4b62b8283d60
malware-analysis is a skill published in the GitHub repository zhaoxuya520/reverse-skill (34,866 stars, last pushed 4d ago), licensed MIT. It adds 36 tokens to every session and 4,452 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.