Memory Dumper

Community

ptn1411

memory-dumper

Dump process memory and scan for secrets, license keys, decryption keys, tokens, and crypto artifacts. Cross-platform: comsvcs.dll / MiniDumpWriteDump on Windows, /proc/mem on Linux.

Overview

Publisher	ptn1411
Repository	`skill`
Skill name	`memory-dumper`
Stars	275
Forks	133
Bundled files	3
Links	Skill source Repository Homepage

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.
3 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by ptn1411 on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/ptn1411/skill/tree/main/memory-dumper
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.

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/ptn1411/skill.git /tmp/skill
mkdir -p .claude/skills
cp -r /tmp/skill/memory-dumper .claude/skills/memory-dumper

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Memory Dumper 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 Memory Dumper 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 Memory Dumper 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.

Memory Dumper

Dump running process memory and scan for embedded secrets — license keys, API tokens, crypto keys, decrypted strings that never touch disk.

Language rule: All skill instructions use English. Final summary presented to the user must be in Vietnamese.

0. Authorization & Routing

Operates under MASTER_POLICY.md §1-§2.

Sibling skill	When
frida-hooker	Hook crypto functions to capture keys at call time
network-interceptor	Cross-reference memory tokens with network traffic
electron-app-analyzer	Find JS strings that match memory artifacts
nuitka-decryptor	Compare decrypted Nuitka blobs with memory dumps

Step 1 — Dump Process Memory

Windows (comsvcs.dll — no extra tools needed)

powershell
python scripts\dump_process.py --pid 1234 --out dumps\target.dmp
python scripts\dump_process.py --name "TargetApp.exe" --out dumps\target.dmp

Windows (ProcDump — Sysinternals)

powershell
python scripts\dump_process.py --pid 1234 --method procdump --out dumps\target.dmp

Linux (/proc/mem)

bash
python scripts/dump_process.py --pid 1234 --out dumps/target.dmp
python scripts/dump_process.py --name "target_app" --out dumps/target.dmp

Requires: elevated privileges (Administrator / root) for full memory access.

Step 2 — Scan Memory Dump

bash
python scripts/scan_memory.py dumps/target.dmp --out analysis/

powershell
python scripts\scan_memory.py dumps\target.dmp --out analysis\

Detects:

License keys: Common serial formats (XXXXX-XXXXX-...), base64 license blobs
API tokens: Bearer tokens, JWT, API keys, OAuth tokens
Crypto keys: AES/RSA key material, high-entropy blocks adjacent to crypto constants
URLs: HTTP(S) endpoints, license server URLs
Strings: UTF-8 and UTF-16 printable strings with context

Options:

--min-entropy 4.5 — Minimum Shannon entropy for key candidate blocks
--key-size 16,32 — Expected key sizes in bytes (AES-128, AES-256)
--cross-ref strings.txt — Cross-reference with known strings from static analysis

Step 3 — Cross-Reference with Static Analysis

Feed scan results back to other skills:

bash
# Compare memory strings with Nuitka .rsrc constants
python scripts/scan_memory.py dumps/target.dmp --cross-ref nuitka_strings.txt --out xref/

# Compare with electron ASAR strings
python scripts/scan_memory.py dumps/target.dmp --cross-ref asar_strings.txt --out xref/

Final Report (Vietnamese)


🧠 Phân tích memory dump hoàn tất:

  📦 Dump size        : <SIZE> MB
  🔤 Strings found    : <COUNT> (UTF-8: X, UTF-16: Y)
  🔑 License keys     : <COUNT>
  🎫 API tokens       : <COUNT>
  🔐 Crypto key cands : <COUNT>
  🌐 URLs found       : <COUNT>
  📊 Cross-ref matches: <COUNT>

  💾 Output: analysis/

Anti-Patterns

❌ Don't	✅ Do
Dump without elevated privileges	Run as Administrator / root
Scan only UTF-8 strings	Always scan both UTF-8 and UTF-16LE
Ignore high-entropy blocks	Entropy analysis catches AES keys
Dump after app exits	Dump while app is running with license active
Skip cross-referencing	Compare memory strings with static analysis output
Use only one dump method	Try comsvcs.dll first, fallback to ProcDump or API

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Memory Dumper AI skill do?

Dump process memory and scan for secrets, license keys, decryption keys, tokens, and crypto artifacts. Cross-platform: comsvcs.dll / MiniDumpWriteDump on Windows, /proc/mem on Linux.

Why use Memory Dumper on TypingMind?

Because you install it once and use it with any model. Memory Dumper 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 Memory Dumper in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/ptn1411/skill/tree/main/memory-dumper. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Memory Dumper?

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 Memory Dumper?

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

Is the Memory Dumper AI skill free?

It is published on GitHub by ptn1411. Check the repository for licensing terms. 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

Deslop

openclaw

OrganizationPopular

Diff-scoped AI-slop cleanup pass: strip comment slop, defensive-check slop, type-laundering, and style drift from the current branch diff before autoreview.

Discord Clawd

Use to talk to the Discord-backed OpenClaw agent/session; not for archive search.

Discrawl

Discord archive: search, sync freshness, DMs, summaries, TUI, repo/release work.

Gitcrawl

GitHub archive: issue/PR search, sync freshness, duplicate clusters, current GitHub handoff, and Gitcrawl repo work.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Memory Dumper

0. Authorization & Routing

Step 1 — Dump Process Memory

Windows (comsvcs.dll — no extra tools needed)

Windows (ProcDump — Sysinternals)

Linux (/proc/mem)

Step 2 — Scan Memory Dump

Step 3 — Cross-Reference with Static Analysis

Final Report (Vietnamese)

Anti-Patterns

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now