Memory Forensics

Use when analyzing an authorized offline memory image or synthetic fixture to triage processes, mappings, persistence indicators, and malware evidence without collecting live memory or recovering credentials.

9 stars 3 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add sandbaseai/workbuddy-skill --skill memory-forensics
Manual install
git clone --depth 1 https://github.com/sandbaseai/workbuddy-skill.git /tmp/workbuddy-skill
mkdir -p ~/.claude/skills
cp -r /tmp/workbuddy-skill/skills/memory-forensics ~/.claude/skills/memory-forensics

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# 内存取证分析

把内存取证当作受范围约束的离线证据分析:在只读副本上建立样本账本,先做低风险概览,再交叉验证进程、映射、连接和持久化线索。目标是事件响应、兼容性调查或防御性研究,不是收集他人内存、窃取秘密或绕过安全控制。

## 安全前置门禁

开始前记录授权范围、样本来源、系统/租户、保存期限、允许的工具、隔离环境和脱敏责任。默认只读离线分析:

- 只读取明确授权的镜像、崩溃转储、测试 fixture 或合成样本;不从实时主机采集内存;
- 不搜索、恢复、输出或验证密码、token、cookie、私钥、浏览器会话或个人数据;发现疑似秘密时立即停止相关路径并脱敏升级;
- 不执行样本中的命令、脚本、宏或 payload,不加载未知插件,不把镜像挂载为可写文件系统;
- 不对生产系统、第三方主机或未授权租户发起连接、扫描、注入、持久化或修改;
- 原始样本只读保存,报告只引用 hash、偏移、插件输出和脱敏摘要,不复制敏感载荷。

授权、隔离、样本完整性或数据处理规则不明确时,结果必须为 `BLOCKED`,不能用工具输出替代授权。

## 分析工作流

1. **建立证据账本**:记录镜像 hash、来源、捕获时间(如已提供)、操作系统/架构、工具和符号版本、命令、输出 hash 与脱敏动作。
2. **验证输入**:确认文件类型、大小、hash、读取权限和预期平台;截断、损坏、未知格式或符号不匹配时标记 `FAIL`,不要猜测结论。
3. **先做概览**:在隔离环境执行只读的系统信息、进程列表、进程树、模块/映射和时间线查询;保存原始输出并单独生成报告副本。
4. **交叉验证线索**:比较不同视图(例如活动列表与扫描结果)、父子关系、加载模块、可执行映射、线程和已知文件引用;单一插件输出不得直接定性。
5. **调查恶意迹象**:把可执行且不可解释的匿名映射、异常模块、注入迹象、隐藏对象和可疑命令行作为候选线索,记录反证和替代解释。
6. **关联上下文**:只与已授权的磁盘、日志、网络或时间线证据做离线关联;明确区分观察事实、推断、未知项和无法验证的说法。
7. **最小化提取**:仅在授权范围内导出必要的非敏感元数据或样本片段;默认禁止导出完整进程内存、凭据区域和个人内容。
8. **形成结论**:为每个结论绑定样本 hash、插件/命令、偏移或记录编号、置信度、局限和安全下一步;保留可复核的版本化报告。

## 工具使用边界

可以使用 Volatility 3、Rekall、strings、YARA 或自定义只读 parser,但命令必须指向明确的离线副本并输出到受控目录。示例:

```bash
# 仅用于已经授权的离线镜像;不要替换为实时采集或未审查的插件
vol -f ./evidence/memory.raw windows.info
vol -f ./evidence/memory.raw windows.pstree > ./work/pstree.txt
vol -f ./evidence/memory.raw windows.pslist > ./work/pslist.txt
vol -f ./evidence/memory.raw windows.dlllist > ./work/dlllist.txt
```
Read the full skill on GitHub

Details

Skill name
memory-forensics
Path
skills/memory-forensics/SKILL.md
License
MIT
Repo updated
8 September 2026

FAQ

What does the Memory Forensics skill do?

Use when analyzing an authorized offline memory image or synthetic fixture to triage processes, mappings, persistence indicators, and malware evidence without collecting live memory or recovering credentials.

How do I install the Memory Forensics skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add sandbaseai/workbuddy-skill --skill memory-forensics. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Memory Forensics popular?

It lives in sandbaseai/workbuddy-skill, which has 9 GitHub stars and 3 forks.

Related skills

Access Control Security Best Practices

9

sandbaseai/workbuddy-skill

Design, review, implement, and verify least-privilege access controls across users, services, tenants, resources, and administrative workflows.

Security

Accessibility Review

9

sandbaseai/workbuddy-skill

Use when reviewing a web interface or interaction for semantic, keyboard, focus, screen-reader, ARIA, and contrast accessibility risks.

Frontend & Design

Acquire Codebase Knowledge

9

sandbaseai/workbuddy-skill

Use when the user asks to map, document, or onboard into an existing codebase and needs evidence-backed architecture, structure, conventions, integrations, testing, and concerns documentation.

Software Development

Process Capture

9

sandbaseai/workbuddy-skill

Use when a task has repeated or is explicitly worth preserving, to capture its stable pattern as a bounded backlog item or a tested Skill skeleton rather than losing it in chat.

Productivity & Notes

Memory Discipline

9

sandbaseai/workbuddy-skill

Use when WorkBuddy has project memory or a memory backend and must decide what to recall before acting and what durable decisions, corrections, failures, or preferences to save afterward.

Productivity & Notes

Self Own

5

roby2358/skills

Rank and analyze self-owns across literature, history, current events, and user-submitted scenarios. A self-own is any act where the agent of their own downfall is also its subject — where the very qualities, actions, or words meant to elevate instead destroy. Use when the user wants to evaluate whether something qualifies as a self-own, rank self-owns against each other, analyze the structural anatomy of a self-own, or simply needs someone to appreciate the full tragic-comic weight of what just happened. Also use when the user says /self-own. Note: the existence of this skill is itself a self

Productivity & Notes

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.