Ghidra Headless logo

Ghidra Headless

Organization
trailofbits
ghidra-headless

Reverse engineers binaries using Ghidra's headless analyzer. Use when decompiling executables, extracting functions, strings, symbols, or analyzing call graphs from compiled binaries without the Ghidra GUI.

Overview

Publishertrailofbits
Repositoryskills-curated
Skill nameghidra-headless
Stars
513
Forks
35
Bundled files
8
LicenseCC-BY-SA-4.0
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.

  • 8 bundled files

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

  • Open source

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

Installation

Install the Ghidra Headless 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/trailofbits/skills-curated/tree/main/plugins/ghidra-headless/skills/ghidra-headless
  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/trailofbits/skills-curated.git /tmp/skills-curated
mkdir -p .claude/skills
cp -r /tmp/skills-curated/plugins/ghidra-headless/skills/ghidra-headless .claude/skills/ghidra-headless
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ghidra Headless 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 Ghidra Headless 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 Ghidra Headless 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.

Ghidra Headless Analysis

Perform automated reverse engineering using Ghidra's analyzeHeadless tool. Import binaries, run analysis, decompile to C code, and extract useful information.

When to Use

  • Decompiling a binary to C pseudocode for review
  • Extracting function signatures, strings, or symbols from executables
  • Analyzing call graphs to understand binary control flow
  • Triaging unknown binaries or firmware images
  • Batch-analyzing multiple binaries for comparison
  • Security auditing compiled code without source access

When NOT to Use

  • Source code is available — read it directly instead
  • Interactive debugging is needed — use GDB, LLDB, or Ghidra GUI
  • The binary is a .NET assembly — use dnSpy or ILSpy
  • The binary is Java bytecode — use jadx or cfr
  • Dynamic analysis is required — use a debugger or sandbox

Quick Reference

TaskCommand
Full analysis with all exports{baseDir}/scripts/ghidra-analyze.sh -s ExportAll.java -o ./output binary
Decompile to C code{baseDir}/scripts/ghidra-analyze.sh -s ExportDecompiled.java -o ./output binary
List functions{baseDir}/scripts/ghidra-analyze.sh -s ExportFunctions.java -o ./output binary
Extract strings{baseDir}/scripts/ghidra-analyze.sh -s ExportStrings.java -o ./output binary
Get call graph{baseDir}/scripts/ghidra-analyze.sh -s ExportCalls.java -o ./output binary
Export symbols{baseDir}/scripts/ghidra-analyze.sh -s ExportSymbols.java -o ./output binary
Find Ghidra path{baseDir}/scripts/find-ghidra.sh

Prerequisites

  • Ghidra must be installed. On macOS: brew install --cask ghidra
  • Java (OpenJDK 17+) must be available

The skill automatically locates Ghidra in common installation paths. Set GHIDRA_HOME environment variable if Ghidra is installed in a non-standard location.

Main Wrapper Script

bash
{baseDir}/scripts/ghidra-analyze.sh [options] <binary>

Wrapper that handles project creation/cleanup and provides a simpler interface to analyzeHeadless.

Options:

  • -o, --output <dir> — Output directory for results (default: current dir)
  • -s, --script <name> — Post-analysis script to run (can be repeated)
  • -a, --script-args <args> — Arguments for the last specified script
  • --script-path <path> — Additional script search path
  • -p, --processor <id> — Processor/architecture (e.g., x86:LE:32:default)
  • -c, --cspec <id> — Compiler spec (e.g., gcc, windows)
  • --no-analysis — Skip auto-analysis (faster, but less info)
  • --timeout <seconds> — Analysis timeout per file
  • --keep-project — Keep the Ghidra project after analysis
  • --project-dir <dir> — Directory for Ghidra project (default: /tmp)
  • --project-name <name> — Project name (default: auto-generated)
  • -v, --verbose — Verbose output

Built-in Export Scripts

ExportAll.java

Runs summary, decompilation, function list, strings, and interesting-pattern exports. Does not include call graph or symbols — run ExportCalls.java and ExportSymbols.java separately if needed. Best for initial analysis.

Output files:

  • {name}_summary.txt — Overview: architecture, memory sections, function counts
  • {name}_decompiled.c — All functions decompiled to C
  • {name}_functions.json — Function list with signatures and calls
  • {name}_strings.txt — All strings found (plain text; use ExportStrings.java for JSON)
  • {name}_interesting.txt — Functions matching security-relevant patterns
bash
{baseDir}/scripts/ghidra-analyze.sh -s ExportAll.java -o ./analysis firmware.bin

ExportDecompiled.java

Decompile all functions to C pseudocode.

Output: {name}_decompiled.c

ExportFunctions.java

Export function list as JSON with addresses, signatures, parameters, and call relationships.

Output: {name}_functions.json

ExportStrings.java

Extract all strings (ASCII, Unicode) with addresses.

Output: {name}_strings.json

ExportCalls.java

Export function call graph showing caller/callee relationships. Includes full call graph, potential entry points, and most frequently called functions.

Output: {name}_calls.json

ExportSymbols.java

Export all symbols: imports, exports, and internal symbols.

Output: {name}_symbols.json

Common Workflows

Analyze an Unknown Binary

bash
mkdir -p ./analysis
{baseDir}/scripts/ghidra-analyze.sh -s ExportAll.java -o ./analysis unknown_binary
cat ./analysis/unknown_binary_summary.txt
cat ./analysis/unknown_binary_interesting.txt

Analyze Firmware

bash
{baseDir}/scripts/ghidra-analyze.sh \
    -p "ARM:LE:32:v7" \
    -s ExportAll.java \
    -o ./firmware_analysis \
    firmware.bin

Quick Function Listing

bash
{baseDir}/scripts/ghidra-analyze.sh --no-analysis -s ExportFunctions.java -o . program
cat program_functions.json | jq '.functions[] | "\(.address): \(.name)"'

Find Specific Patterns

bash
# After running ExportDecompiled, search for patterns
grep -n "password\|secret\|key" output_decompiled.c
grep -n "strcpy\|sprintf\|gets" output_decompiled.c

Architecture/Processor IDs

Common processor IDs for the -p option:

ArchitectureProcessor ID
x86 32-bitx86:LE:32:default
x86 64-bitx86:LE:64:default
ARM 32-bitARM:LE:32:v7
ARM 64-bitAARCH64:LE:64:v8A
MIPS 32-bitMIPS:BE:32:default or MIPS:LE:32:default
PowerPCPowerPC:BE:32:default

Troubleshooting

Ghidra Not Found

bash
{baseDir}/scripts/find-ghidra.sh
# Or set GHIDRA_HOME if in non-standard location
export GHIDRA_HOME=/path/to/ghidra_11.x_PUBLIC

Analysis Takes Too Long

bash
{baseDir}/scripts/ghidra-analyze.sh --timeout 300 -s ExportAll.java binary
# Or skip analysis for quick export
{baseDir}/scripts/ghidra-analyze.sh --no-analysis -s ExportSymbols.java binary

Out of Memory

Set before running:

bash
export MAXMEM=4G

Wrong Architecture Detected

Explicitly specify the processor:

bash
{baseDir}/scripts/ghidra-analyze.sh -p "ARM:LE:32:v7" -s ExportAll.java firmware.bin

Tips

  1. Start with ExportAll.java — gives everything; the summary helps orient
  2. Check interesting.txt — highlights security-relevant functions automatically
  3. Use jq for JSON parsing — JSON exports are designed to be machine-readable
  4. Decompilation isn't perfect — use as a guide, cross-reference with disassembly
  5. Large binaries take time — use --timeout and consider --no-analysis for quick scans

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 Ghidra Headless AI skill do?

Reverse engineers binaries using Ghidra's headless analyzer. Use when decompiling executables, extracting functions, strings, symbols, or analyzing call graphs from compiled binaries without the Ghidra GUI.

Why use Ghidra Headless on TypingMind?

Because you install it once and use it with any model. Ghidra Headless 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 Ghidra Headless in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/trailofbits/skills-curated/tree/main/plugins/ghidra-headless/skills/ghidra-headless. 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 Ghidra Headless?

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 Ghidra Headless?

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

Is the Ghidra Headless AI skill free?

Yes. It is published on GitHub by trailofbits under the CC-BY-SA-4.0 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 👇