Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Malware Analysis

ASecurity

Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior.

477 stars
0 votes
0 copies
0 views
Added 9/23/2026
ai-agentspythonrustgophpshellbashgitapi

Works with

cliapi

Security Analysis

A92/100
mediumInstalls packages at runtime which could introduce malicious dependencies

Pro scans all 3 files and shows the line behind each finding

Scanned 9/23/2026

$npx -y skills add coco-research/coco --skill malware-analysis --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Malware Analysis?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Malware Analysis
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/coco-research-malware-analysis/badge)](https://www.skillsdirectory.com/skills/coco-research-malware-analysis)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: malware-analysis
description: Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior.
user-invocable: true
---
# Malware Analysis

## 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

```bash
# 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
```

```text
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)

```text
□ 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

```text
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
```

### Phase 3: 沙箱动态分析

```text
自动化沙箱:
□ Joe Sandbox / ANY.RUN / Triage: 商业沙箱
□ CAPE Sandbox: 开源 + YARA 集成(推荐)
□ ASD Azul: 开源恶意软件分析平台(2026 新发布)
□ Cuckoo Sandbox: 经典开源(逐步被 CAPE 取代)

调试起手式(补丁 7+10 · MUST 顺序,用户态调试器):
□ ① TLS 回调断点 → ② 入口点 EP 断点 → ③ 敏感 API 断点 → ④ ExitProcess/退出路径保底断点
□ ExitProcess 触发时:不急着重启;立即 dump memory,路径写入 Evidence(补丁 10)

监控重点:
□ 进程创建: CreateProcess / ShellExecute
□ 文件操作: WriteFile → 勒索? DeleteFile → Wiper?
□ 注册表: Run/RunOnce 持久化
□ 网络: HTTP/DNS → C2 通信
□ 内存: VirtualAllocEx → 进程注入
□ 服务: CreateService → 持久化
□ IAT 修复失败 / 自校验闪退样本:敏感 API + CreateFile/GetFileSize 断点 / 硬件执行断点 / 内存搜索

无行为应急分支(MUST):
□ 沙箱无行为、秒退或无限休眠 → 检查反调试/反虚拟机(CPUID、计时、环境特征)
□ 尝试硬件断点绕过、补丁检测点、或换物理机/更高保真环境
□ 将「无行为 + 条件」写入 Evidence;禁止无条件写成「样本无害」

时间盒(补丁 9 · SHOULD 默认,可覆盖):
□ 静态深挖约 15 分钟无关键路径 → 强制转入本 Phase 动态
□ 动态单步约 200 条指令无恶意线索 → 强制回静态字符串/交叉引用重锚

反调试/混淆旁路(Issue #65 A–T · 详见 reverse-engineering/anti-analysis.md 菜谱):
□ P0:CPUID / RDTSC / PEB / NtQueryInformationProcess → 记录检测点后 lab 绕过或换环境(E-anti-debug-*)
□ P0:干净 IAT → API 哈希动态解析(bp GetProcAddress,E-api-hash)
□ P0:strings 空 → 串解密例程 + 宽字符串 UTF-16(E-string-decrypt / E-wide-strings)
□ P0:可疑签名 → SigCheck;无效/吊销不降威胁(E-sig-forge)
□ P1:进程名扫描 / VEH / int3·DR / 重叠节 / Overlay / .rsrc / Delay-Load
□ H/S 平坦化与不透明谓词 → ollvm-deobfuscation.md(不在此复制长文)
□ 绕过失败也写 Evidence;禁止反调试退出 = 样本无害

非 PE / 脚本 / DLL 补洞(Issue #65 U–AV · 详见 reverse-engineering/references/nonpe-format-cookbook.md):
□ bat/cmd:SET 拼接还原(U)→ E-batch-deobf;UTF-16 BOM(V);REM/GOTO 淹没(W)
□ PowerShell:多层 Base64/Gzip(X)逐层 Evidence;IEX 拼接/反转(Z)
□ VBA:Stomping/P-Code(AA);Chr/Base64(AB);自修改宏(AC)
□ DLL:TLS+DllMain(AJ);导出异常/无导出(AK/AL);Delay-Load 见 A–T R(AM);侧加载/反射(AO/AP)
□ JS/APK/驱动:路由 js-reverse / apk-reverse / kernel-driver-reverse + cookbook,不在此复制长文
```

### Phase 4: YARA 规则编写

```yara
// 规则结构
rule MalwareFamily_Example {
    meta:
        description = "检测 Example 恶意软件家族"
        author = "分析者"
        date = "2026-05"
        severity = "high"
        hash = "d41d8cd98f00b204e9800998ecf8427e"
        mitre_id = "T1055"  // Process Injection

    strings:
        // 字符串匹配
        $str1 = "C2_SERVER_URL" ascii wide
        $str2 = "payload.dat" ascii

        // 十六进制匹配
        $hex1 = { 8B 45 ?? 50 FF 15 [4] 85 C0 }
        // 操作码序列: mov eax, [ebp-?]; push eax; call [import]; test eax, eax

        // 正则匹配
        $re1 = /https?:\/\/[a-z0-9.-]+\/[a-z]{3,8}\.php/ ascii

    condition:
        // 组合条件
        uint16(0) == 0x5A4D and     // MZ 头
        filesize < 500KB and
        (2 of ($str*) or $hex1)
}
```

### Phase 5: Sigma 规则生成

```yaml
# 行为检测规则
title: Suspicious Process Injection via CreateRemoteThread
id: 5a3d2c1b-1234-5678-9abc-def012345678
status: experimental
description: 检测使用 CreateRemoteThread 的进程注入行为
author: 分析者
date: 2026/05/25
tags:
    - attack.t1055          # Process Injection
    - attack.t1055.001      # DLL Injection
logsource:
    category: process_creation
    product: windows
detection:
    selection:
        Image|endswith: '\powershell.exe'
        CommandLine|contains:
            - 'CreateRemoteThread'
            - 'VirtualAllocEx'
            - 'WriteProcessMemory'
    condition: selection
falsepositives:
    - 合法的调试工具
level: high
```

### Phase 6: IOC 提取与情报

```text
IOC 类型分类:
□ 网络 IOC:
  - IP: C2 地址(注意时效性)
  - Domain: DGA 算法生成的域名(rsnkfda.com, xpqmje.net)
  - URL: Payload 托管地址
  - User-Agent: 自定义 UA 字符串

□ 主机 IOC:
  - 文件路径: %APPDATA%\Microsoft\Crypto\RSA\*.dat
  - 注册表: HKCU\Software\Microsoft\Windows\CurrentVersion\Run\
  - Mutex: Global\{GUID} 互斥体名称
  - 服务名: 伪装成系统服务的名称

□ 行为 IOC:
  - MITRE ATT&CK 技术 ID (T1055, T1003, T1571...)
  - Sigma 规则 → SIEM 集成
  - YARA 规则 → 端点检测

□ 静态 IOC:
  - 编译时间戳(可伪造)
  - PDB 路径(含开发者信息)
  - 节名异常(非标准 .text/.data)
  - 导入表异常组合(如勒索软件 CryptEncrypt + DeleteShadowCopies)
```

## 反分析技术速查

| 技术 | 检测方法 | YARA 特征 |
|------|---------|----------|
| 虚拟机检测 | WMI Win32_BIOS/VideoController/Processor | `Win32_` 字符串 + 特定厂商名 |
| 沙箱检测 | 磁盘 < 60GB, RAM < 2GB, 单核 CPU | GlobalMemoryStatusEx 调用模式 |
| 调试器检测 | IsDebuggerPresent, CheckRemoteDebuggerPresent | PEB.BeingDebugged 偏移访问 |
| 定时逃逸 | Sleep(300000) 后执行恶意行为 | NtDelayExecution 长参数 |
| 地理位置检测 | 检查键盘布局/时区 → 排除 CIS 国家 | GetKeyboardLayoutList 调用 |
| 父进程检测 | explorer.exe vs cmd.exe | 进程名字符串比较 |
| API 直接 syscall | 绕过 EDR hook | syscall 指令 + SSN 解析 |

## 多 Agent 自动化分析 (SentinelHive 架构)

```text
┌─────────────────────────────────────────────────┐
│                  Hive Director                    │
│          (Claude Opus 编排 + 仲裁)                │
└──────┬──────┬──────┬──────┬──────┬───────┘
       │      │      │      │      │
   ┌───┘  ┌───┘  ┌───┘  ┌───┘  ┌───┘
   ▼      ▼      ▼      ▼      ▼      ▼
Triage  RE    Behav  Intel  Detect Remed
 快速   反编译  行为   威胁   规则   修复
 分诊   静态   动态   情报   YARA  方案
                          Sigma
```

## 工具链

| 工具 | 用途 | 获取 |
|------|------|------|
| Ghidra / IDA Pro | 深度反编译 | ghidra-sre.org |
| CAPE Sandbox | 开源恶意软件沙箱 | GitHub: kevoreilly/CAPEv2 |
| ASD Azul | 大规模自动化分析 | GitHub: ASD |
| YARA | 模式匹配规则引擎 | `pip install yara-python` |
| Sigma | SIEM 行为检测规则 | GitHub: SigmaHQ/sigma |
| FLOSS | 去混淆字符串提取 | `pip install flare-floss` |
| Detect It Easy | 壳/编译器检测 | GitHub: horsicq/Detect-It-Easy |
| pe-sieve | 进程内存扫描 | GitHub: hasherezade/pe-sieve |
| VirusTotal API | 多引擎扫描 | virustotal.com |
| MalwareBazaar | 恶意软件样本库 | bazaar.abuse.ch |

## 参考

- `references/yara-sigma-rules.md` — YARA + Sigma 编写方法论
- `references/sandbox-orchestration.md` — 沙箱编排与自动化
- `references/anti-analysis-techniques.md` — 94 种反分析技术检测
- `../reverse-engineering/references/re-agent-workflow.md` — IAT 铁律与六阶段门闩(Issue #65)
- `../reverse-engineering/anti-analysis.md` — Agent 响应菜谱 A–T(反调试/混淆旁路)
- `../reverse-engineering/references/nonpe-format-cookbook.md` — 非 PE/多格式菜谱 U–AV(脚本/宏/JS/驱动/DLL/Android)
- `../reverse-engineering/references/ollvm-deobfuscation.md` — 平坦化/不透明谓词(H/S)

Attribution

coco-researchcoco-research
View sourceSee grades on GitHubMore from coco-research →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →