Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    reverse engineering kit

    1

    An evidence-based reverse engineering kit for verifiable analysis of binaries, APKs, and network protocols.

    Free

    Security scanned
    reverse engineering kit

    reverse engineering kit

    Example session with this skill installed

    I need to analyze this Android APK to find where it sends user data. I have authorization for this research. Run the initial triage.

    • Read your context and instructions
    • Compiled the reverse engineering kit

    I have initialized the analysis environment and performed the safety check. The authorization details have been recorded in notes.md, and the target hash is logged.

    Triage Results: Android Analysis

    FieldValue
    Fileoriginal/app-release.apk
    Familyandroid
    Packagecom.example.tracker
    Main Activitycom.example.tracker.MainActivity
    Signalsokhttp3, firebase-analytics, custom-obfuscation
    Read Nextreferences/android.md, references/anti-analysis.md

    The triage identified OkHttp3 and Firebase signatures. I have created the re-work/app-release/ directory structure. Initial impression: The app uses standard networking libraries but shows signals of custom obfuscation in the lib/ directory.

    Next steps

    1. Run scripts/decompile_apk.py to extract the manifest and Java sources.
    2. Execute scripts/find_endpoints.py to identify hardcoded URLs and API paths.
    3. Formulate a hypothesis regarding the data exfiltration trigger in notes.md.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Software analysis often relies on guesswork and unverified decompilation. This skill provides an evidence-first framework for reverse engineering binaries, mobile apps, and network protocols, ensuring every claim is backed by reproducible tests.

    What it does

    • Automated Triage identifies file types, headers, and potential packers for native, Android, and JS targets.
    • Ledger Management tracks findings across four confidence levels, from initial inference to verified proof.
    • Multi-Target Analysis drives Ghidra for native code, jadx for APKs, and specialized tools for Electron or minified JS.
    • Evidence Verification runs Python-based differential tests to confirm that recovered functions or algorithms match original behavior.
    • Safety Enforcement implements strict gates for authorization, environment isolation, and data redaction.

    How it works

    1. Safety and Setup: Run doctor.py to check tool chains, establish authorization in notes.md, and hash original files.
    2. Triage and Route: Execute triage.py to determine the binary family and select the appropriate playbook for analysis.
    3. Hypothesis Loop: Add claims to the ledger using ledger.py, moving findings from inferred to observed via tool output.
    4. Verification: Write Python checks in tests/ and use ledger.py verify to promote findings to confirmed status.
    5. Reporting: Generate a structured REPORT.md using make_report.py once all mandatory sections and evidence are logged.

    Frameworks & tools

    The kit integrates with Ghidra (headless), LIEF, rizin, jadx, apktool, webcrack, and Frida. It requires Python 3.10+ for the orchestration scripts and ledger system.

    Why this beats prompting it yourself

    Standard prompts often hallucinate logic from decompiled code without verification. This skill enforces a test-driven workflow where claims must survive differential analysis and automated auditing before being accepted.

    Use cases

    • Recovering source logic from minified JavaScript or obfuscated Electron apps.
    • Analyzing Android APKs to map API endpoints and internal data structures.
    • Decoding proprietary network protocols from pcap/pcapng captures.
    • Solving complex CTF challenges or crackmes with a formal evidence ledger.

    Known limitations

    Does not support .NET, Java JARs, Python bytecode (pyc), or iOS IPA files in the current version. Requires a pre-configured VM for dynamic analysis and script-based verification.

    No support for .NET, JAR, pyc, or iOS. Requires external tools like Ghidra/Jadx. Dynamic analysis requires a user-provided VM.

    How to use

    1. 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. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    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

    Free forever

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 5 days ago

    • Free with an Agensi account

    Requires

    Python
    Claude Code
    Ghidra 12.2 + JDK 25
    rizin
    LIEF
    UPX 5.3
    jadx 1.5.6
    Node 22 or 24
    Kaitai Struct compiler 0.11
    Frida 17.25
    Ida Pro MCP
    git
    uv (Python tool runner)
    macOS

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Write Files
    Environment Variables
    Browser
    Listed5 days ago

    What's inside

    Frequently Asked Questions

    Unlike standard LLM prompts that guess at code logic, this skill uses a 'Ledger' system to track findings through four confidence levels, requiring Python-based differential tests to verify that recovered logic matches the original binary's behavior.

    The kit is designed for native binaries (via Ghidra/rizin), Android APKs (via jadx/apktool), and JavaScript/Electron apps; however, it currently does not support .NET, Java JARs, or iOS (IPA) files.

    You receive a suite of Python orchestration scripts (including the Ledger and Triage systems), specialized analysis playbooks for different targets, and a structured reporting framework to document your findings.

    Yes, you will need a Python 3.10+ environment with tools like Ghidra, jadx, and LIEF installed; the kit includes a `doctor.py` utility to help you verify your toolchain and environment isolation before you begin.

    The skill is designed to work with advanced AI agents capable of executing Python scripts and managing local file systems, ensuring the agent can drive the underlying security tools autonomously.

    The kit includes 'Safety Enforcement' gates that require explicit authorization in a `notes.md` file and support environment isolation to ensure analysis is performed securely and ethically.

    New in Testing & Debugging