Skip to content

Binary Ninja Reverse Engineering

Guides an agent through authorized binary analysis in Binary Ninja, with optional MCP bridge integration.

Stars
43,969
Licence
MIT
Files
2 files

What it does

This skill teaches an AI agent how to analyze compiled programs (binaries) using Binary Ninja, a commercial reverse engineering tool. Once installed, the agent follows a safe, structured workflow: it checks scope, records file details like hashes and imports, reads decompiled logic at different intermediate levels, and reports findings with addresses and evidence. It also covers optional connection to Binary Ninja through a localhost bridge, and it asks for care before making any changes such as patches or saved-file writes.

Great for

  • Security researchers doing authorized analysis of software they are permitted to examine
  • Developers or students learning how to read compiled code with Binary Ninja
  • Analysts who want an independent cross-check of IDA, Ghidra, or radare2 results

Skip it if

  • Analyzing software without authorization, since the skill assumes a confirmed, in-scope target and does not itself verify permission
  • Users without a valid Binary Ninja license, because Binary Ninja is commercial software that must be installed manually
  • Enabling the optional third-party MCP bridge on a shared network, since the skill itself warns against network exposure and the bridge is a GPL-3.0 community plugin, not an official Vector 35 component

Try asking

  • “Analyze this binary in Binary Ninja and list its imports, exports, and interesting strings with addresses”
  • “Decompile the function at this address to HLIL and explain its logic with supporting references”
  • “Cross-check the findings from my Ghidra analysis using Binary Ninja's MLIL data flow”
  • “Review the proposed byte patch on a copy of this binary and document the original bytes”
Step-by-step guide: how to use Binary Ninja Reverse EngineeringInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the MIT licence and an attribution note.

    binary-ninja-reverse.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip binary-ninja-reverse.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip binary-ninja-reverse.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Only use this skill with binaries you are authorized to analyze, and state the scope before starting
  • Work on a copy of any file you plan to patch or modify, and keep the original artifact
  • Leave the MCP bridge disabled unless you explicitly need it, and keep the listener on 127.0.0.1

What's inside

  • agents/openai.yaml
  • SKILL.md

Redistributed unmodified from zhaoxuya520/reverse-skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.