Reverse Engineering logo

Reverse Engineering

Community
hypnguyen1209
reverse-engineering

Use when reverse-engineering a binary or firmware — static triage + decompilation (Ghidra/IDA/Binary Ninja), dynamic instrumentation (GDB/Frida 17/angr), anti-reversing & packer bypass, OLLVM/VM deobfuscation, UEFI/BIOS RE & Secure Boot research, patch-diffing for n-days

Overview

Publisherhypnguyen1209
Repositoryoffensive-claude
Skill namereverse-engineering
Stars
396
Forks
71
Bundled files
19
LicenseMIT
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.

  • 19 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hypnguyen1209 on GitHub. Read the source before you install it.

Installation

Install the Reverse Engineering 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/hypnguyen1209/offensive-claude/tree/main/skills/reverse-engineering
  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/hypnguyen1209/offensive-claude.git /tmp/offensive-claude
mkdir -p .claude/skills
cp -r /tmp/offensive-claude/skills/reverse-engineering .claude/skills/reverse-engineering
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Reverse Engineering 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 Reverse Engineering 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 Reverse Engineering 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.

Reverse Engineering

When to Activate

  • Triaging an unknown compiled binary (ELF/PE/Mach-O) or stripped/obfuscated sample for vulns or capability.
  • Decompiling proprietary code and recovering structure/types (incl. AI/MCP-assisted Ghidra/Binary Ninja).
  • Unpacking & devirtualizing protected binaries (VMProtect 3.x, Themida, OLLVM control-flow flattening).
  • Defeating anti-debugging / anti-VM / anti-Frida so dynamic analysis can proceed.
  • Firmware extraction & UEFI/BIOS RE, Secure Boot bypass research, persistent pre-OS implant analysis.
  • Patch diffing a Patch-Tuesday/CVE fix to recover root cause and build an n-day trigger.
  • Reverse engineering an unknown wire protocol or proprietary file format for fuzzing/parsing.

Technique Map

TechniqueATT&CKCWEReferenceScript
Binary triage (format/arch/mitigations/strings/imports)T1592.002, T1518.001CWE-1395references/static-triage-decompilation.mdscripts/triage.py
Headless decompilation (Ghidra 11.4 / r2 / IDA)T1592.002CWE-noinforeferences/static-triage-decompilation.mdscripts/triage.py
AI/MCP-assisted RE (Sidekick / GhidrAssistMCP / LLM4Decompile)T1592.002CWE-noinforeferences/static-triage-decompilation.md-
Dynamic debugging (GDB/GEF, x64dbg, conditional bps)T1622CWE-noinforeferences/dynamic-instrumentation.md-
Frida 17 instrumentation + SSL-pin/JNI hookingT1622, T1562.001CWE-noinforeferences/dynamic-instrumentation.mdscripts/frida_universal.js
Symbolic / concolic execution (angr, Triton)T1480.001CWE-noinforeferences/dynamic-instrumentation.mdscripts/deflatten_triton.py
Anti-debug detection & bypass (PEB/ptrace/HW-bp/timing)T1622, T1497.001CWE-noinforeferences/anti-reversing-bypass.mdscripts/antidebug_unhook.py
Anti-VM / sandbox-evasion neutralizationT1497, T1497.003CWE-noinforeferences/anti-reversing-bypass.mdscripts/antidebug_unhook.py
Packer unpack → OEP dump (UPX/runtime packers)T1027.002, T1620CWE-noinforeferences/anti-reversing-bypass.mdscripts/antidebug_unhook.py
String / API-hash deobfuscation (Unicorn emulation)T1027.013, T1140, T1027.007CWE-noinforeferences/deobfuscation.mdscripts/string_decrypt_emu.py
OLLVM control-flow-flattening de-flatteningT1027.009, T1027CWE-noinforeferences/deobfuscation.mdscripts/deflatten_triton.py
VM-protector devirtualization (VMProtect 3.x / Themida)T1027.009CWE-noinforeferences/deobfuscation.mdscripts/deflatten_triton.py
Firmware extraction (binwalk/squashfs/QEMU emulation)T1542.001CWE-1263references/firmware-uefi.mdscripts/uefi_triage.py
UEFI/BIOS RE + Secure Boot bypass researchT1542.001, T1542.003CWE-347references/firmware-uefi.mdscripts/uefi_triage.py
Patch diffing → n-day root cause (BinDiff/Diaphora/ghidriff)T1203, T1592.002CWE-noinforeferences/patch-diffing-protocol.mdscripts/patchdiff_fetch.py
Protocol / file-format inference (Netzob/Kaitai)T1592.002CWE-noinforeferences/patch-diffing-protocol.mdscripts/proto_infer.py

Quick Start

bash
# 0. Triage: format, arch, mitigations, packer entropy, strings, imports, capabilities → JSON
python3 scripts/triage.py ./sample -o out/triage.json

# 1. Headless decompile to C (Ghidra 11.4 analyzeHeadless wrapper inside triage.py --decompile)
python3 scripts/triage.py ./sample --decompile --ghidra "$GHIDRA_HOME" -o out/

# 2. If packed/protected → defeat anti-debug, dump OEP (run under x64dbg+ScyllaHide on Windows)
python3 scripts/antidebug_unhook.py --scan ./sample      # enumerate anti-debug primitives first

# 3. Dynamic: attach Frida (Android/Linux/Win), universal SSL-unpin + native trace
frida -U -f com.target.app -l scripts/frida_universal.js --no-pause

# 4. Deobfuscate: emulate string decryptor over all xrefs; de-flatten OLLVM with Triton
python3 scripts/string_decrypt_emu.py ./sample --func 0x401500 --auto-xref -o out/strings.txt
python3 scripts/deflatten_triton.py ./sample --func 0x401abc -o out/cfg.dot

# 5. Firmware: carve + identify + map UEFI DXE/PEI attack surface, scan for PKfail/known hashes
python3 scripts/uefi_triage.py firmware.bin -o out/fw/

# 6. n-day: fetch pre/post-patch Windows binary from winbindex and diff
python3 scripts/patchdiff_fetch.py --pe afd.sys --kb-after KB5050000 -o out/diff/

# 7. Unknown protocol: infer fields/state machine from a pcap, emit Kaitai + Wireshark dissector
python3 scripts/proto_infer.py capture.pcap --port 4444 -o out/proto/

OPSEC & Detection (summary)

TechniqueTelemetry / IOCDetection (Sigma/EDR)OPSEC note
Static triage / decompileNone (offline on analyst box)N/A — runs in labAnalyze copies in an isolated, snapshotted VM; never on the target
Frida / dynamic hookingfrida-agent.so in /proc/self/maps, port 27042, gum-js-loop/gmain threads, ptrace on targetApp-side RASP (Talsec/DeepID), frida-string scans, EDR userland hook tripwiresRename agent, use gadget+-l script mode, embed gadget in APK to dodge port checks
Anti-debug bypassDebug registers DR0-7 set, PEB.BeingDebugged flips, hooked Nt* prologuesSelf-integrity checks, KiUserExceptionDispatcher checks, TitanHide-vs-malware arms racePrefer kernel TitanHide/HyperHide for hardened packers; snapshot before each run
Packer/OEP dumpNew RWX region, IAT rebuild, written dump.exe on diskEDR RWX-alloc + tail-jump heuristics (lab only)All in lab; dumped sample is for analysis, not redeployment
String/API-hash decrypt (Unicorn)None on target (offline emulation)N/APure offline; safe — no sample execution of network/FS code
Firmware / SPI flash dumpHardware: chip-clip on SPI; software: chipsec/flashrom readsBoot Guard / measured boot (TPM PCRs), Binarly/CHIPSEC verifiersPhysical/authorized only; flashing back a modded image is destructive & loud
Secure Boot bypass researchNew unsigned bootloader in ESP, MokList/dbx anomalies, unexpected bootmgfw hashMeasured boot PCR[0/2/4/7] drift, dbx revocation checks, ESET/Binarly scannersLab VMs / disposable hardware; document, never persist a real implant
Patch diffingNone on target (fetches public binaries)N/APublic Microsoft/distro binaries; n-day PoC stays in lab until disclosure/ROE
Protocol inferenceReplays captured/crafted packets at the serviceIDS on malformed/replayed frames; rate anomaliesThrottle active probes; prefer passive pcap when a live target is in scope

Deep Dives

  • references/static-triage-decompilation.md — File/arch/mitigation triage, entropy & packer ID, capability detection (capa), Ghidra 11.4 analyzeHeadless + PyGhidra, r2/rizin & IDA decompile flows, and the 2025 AI/MCP-assisted layer (Binary Ninja Sidekick, GhidrAssistMCP, LLM4Decompile / SK²Decompile) with verification discipline.
  • references/dynamic-instrumentation.md — GDB/GEF & x64dbg workflows, conditional/commands breakpoints, Frida 17 internals (Interceptor/Stalker/Java), universal SSL-unpin + JNI tracing, and angr/Triton symbolic + concolic execution with backward slicing for path/value recovery.
  • references/anti-reversing-bypass.md — Anti-debug taxonomy (PEB flags, NtSetInformationThread/ThreadHideFromDebugger, DR0-7 / GetThreadContext, KiUserExceptionDispatcher, NtClose, INT 2D, rdtsc timing, Linux ptrace/TracerPid), anti-VM/al-khaser, ScyllaHide/TitanHide, and runtime-packer OEP dumping.
  • references/deobfuscation.md — String & API-hash decryption via Unicorn emulation, OLLVM control-flow-flattening de-flattening (dispatcher recovery, Triton backward slicing à la LummaC2), MBA simplification, and VM-protector devirtualization (NoVmp/VTIL, Titan, Triton lifting) for VMProtect 3.x / Themida.
  • references/firmware-uefi.md — binwalk/unblob carving, squashfs/JFFS2 extraction, QEMU+afl emulation, UEFI volume/DXE/PEI parsing (UEFITool/chipsec), SMM callout & NVRAM variable surface, and Secure Boot bypass research with the verified 2024-2025 chain: LogoFAIL (CVE-2023-40238), PKfail (CVE-2024-8105), CVE-2024-7344, BlackLotus/Bootkitty context.
  • references/patch-diffing-protocol.md — winbindex binary acquisition, MSU/CAB extraction, BinDiff/Diaphora/ghidriff function-level diffing, LLM-assisted triage (PatchWatch/DiffRays) with hallucination caveats, late-2025 kernel targets (cldflt.sys, win32k, CLFS), plus network/file-format protocol RE (Netzob, Kaitai Struct, BinPRE-style field inference).
  • references/rr-time-travel.md — deterministic record/replay root cause: rr record/replay, reverse-continue/stepi + hardware watchpoints to the corrupting write, the auditable trace in the scoped workspace; emits the trace_proof artifact. Backed by scripts/rr_root_cause.sh (degrades gracefully where rr is absent). Runs in .devcontainer/.
  • references/coverage-reachability.md — proving the vulnerable line/function actually executed: gcov line-hit (build --coverage, run the witness, assert the line is not #####) and -finstrument-functions/rr/uftrace function traces; the coverage_proof/trace_proof the native-bug bar in validate_findings.py requires before [CONFIRMED].
  • references/patch-diffing-protocol.md is fed by scripts/cve_diff.py — multi-source canonical fix-commit discovery (OSV/NVD/GitHub Advisories) with de-dup by (repo, sha) + OSV GIT-range fixed events, then a scope-gated, git_safe-hardened clone + git diff fix^..fix. Use it to locate the patch before BinDiff/ghidriff; chain into /engage.crash for root-cause + exploitability.

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 Reverse Engineering AI skill do?

Use when reverse-engineering a binary or firmware — static triage + decompilation (Ghidra/IDA/Binary Ninja), dynamic instrumentation (GDB/Frida 17/angr), anti-reversing & packer bypass, OLLVM/VM deobfuscation, UEFI/BIOS RE & Secure Boot research, patch-diffing for n-days

Why use Reverse Engineering on TypingMind?

Because you install it once and use it with any model. Reverse Engineering 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 Reverse Engineering in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hypnguyen1209/offensive-claude/tree/main/skills/reverse-engineering. 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 Reverse Engineering?

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 Reverse Engineering?

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

Is the Reverse Engineering AI skill free?

Yes. It is published on GitHub by hypnguyen1209 under the MIT 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 👇