- Home
- Skills
- Agents & Orchestration
- reverse engineer anything
Works with the AI Agents you already use
reverse engineer anything
Reverse engineer native binaries, web apps, and firmware using deep static and runtime analysis.
$10
About this skill
Static analysis of a source repository isn't enough when the behavior you need to understand is locked inside a compiled binary, a minified Electron bundle, or a firmware image. This skill provides the specialized toolset needed to tear down shipped artifacts, recover metadata, and observe runtime behavior without access to the original source.
What it does
- Multi-target analysis works with native binaries, managed .NET assemblies, Android APKs, Electron ASARs, and firmware images.
- Deep inspection recovers Go module metadata, Rust dependency graphs, EVM bytecode interfaces, and Unity IL2CPP string literals.
- Runtime observation captures browser scenarios, traces native values, and analyzes live Electron targets or network traffic (HAR/SAZ).
- Evidence management maintains a retained ledger of findings with parent IDs for paging through large datasets without hitting transport limits.
- Environment bundling exports web application states into AgentEnv bundles for consistent reproduction across different agents.
How it works
- Identify the target by providing a local path to a binary, archive, or browser endpoint to determine the appropriate analysis route.
- Bind the provider using tools like Ghidra, IDA Pro, or native REA engines to initialize the analysis session.
- Query the artifact starting with high-level summaries or inventories before drilling into specific functions, modules, or resource trees.
- Corroborate findings by matching static evidence against runtime instrumentation or version comparisons.
Frameworks & tools
REA integrates with professional reverse engineering suites including Ghidra, IDA Pro, and Kuna. It leverages low-level utilities like TShark for packets, WABT for WebAssembly, sigrok for signals, and binwalk for firmware extraction.
Why this beats prompting it yourself
Generic LLM prompts fail when confronted with raw hex, complex control flow graphs, or proprietary archive formats. This skill provides the structured MCP interface needed to manage multi-gigabyte analysis databases, handle transport-layer truncation, and maintain strict evidence-based reasoning across long investigations.
Use cases
- Security audits of third-party binaries where source code is unavailable.
- Interoperability research to document undocumented APIs or data formats.
- Version regression analysis to find logic changes between two shipped builds.
- Malware triage by inspecting PE imports, TLS callbacks, and code signatures.
Known limitations
Does not install external prerequisites like Java, Ghidra, or Homebrew. Native runtime tools require specific OS-level permissions and headers. Binary signatures are identified but not cryptographically verified.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
Requires external engines (Ghidra, IDA, TShark) for specific deep analysis. Runtime tools need host-level permissions. Doesn't verify signature authenticity.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 4 days ago
Mac only
- Software
Pythonrea-agents
Node.js