reverse-skill: router for authorized security and reverse-engineering work
zhaoxuya520/reverse-skill
A toolkit for security professionals. When you give your AI assistant a reverse-engineering or penetration-testing job, it picks a fitting method, checks which tools are on your machine, and follows a set workflow. It is built for offensive security work you are authorized to perform, and it stays read-only until you grant written permission for the target.
Pack description by its author: “A toolkit for security professionals. When you give your AI assistant a reverse-engineering or penetration-testing job, it picks a fitting method, checks which tools are on your machine, and follows a set workflow. It is built for offensive security work you are authorized to perform, and it stays read-only until you grant written permission for the target.”
Research and scienceChanges how your assistant works, all the timeKnowledge and rules for your assistantGives your assistant new abilities with scripts
1. Changes your files
Skills that write or edit files: apk-reverse.
github.com/zhaoxuya520/reverse-skill/blob/cab634b/2. Runs code on your machine
First run: A script scans your machine for installed security tools and writes a local tool-index file. Each task: A router script reads the routing table and picks the specialist module for the task.
github.com/zhaoxuya520/reverse-skill/blob/cab634b/3. Sends data
This is offensive security tooling for authorized work only; the project itself says unauthorized use is strictly prohibited. Its modules include techniques that defeat protections (evading security software, credential extraction, root and certificate-pinning bypass), its scripts can install tools and reach the network once you approve, and it ships an "agent obedience" playbook plus insistent wording that pushes the assistant to execute rather than acknowledge. Use only against targets you own or are authorized to assess, read the rules before activating, and approve each side effect yourself.
github.com/zhaoxuya520/reverse-skill/blob/cab634b/4. Commercial use
MIT for the core; CTF-Sandbox-Orchestrator is GPLv3 and outside tools keep their own licenses
github.com/zhaoxuya520/reverse-skill/blob/cab634b/Checked against the pack's files at commit cab634b, on Oct 30, 2026. Tap a verdict to see its source.How we checkedReport an error
The pack has changed since AgentGid checked it on Oct 30, 2026. Some details may be out of date.
Good for you if
- You do authorized security testing (reverse engineering, pen tests, CTF, malware analysis) with an AI assistant
- You want the assistant to pick a set method and the right tool instead of guessing commands
- You work across many target types: Android apps, binaries, web, firmware, network captures
Probably not for you if
- You are not doing security work you are allowed to perform
- You want a one-click tool: it asks for written authorization and touches no target until you grant it
- You do not use an AI coding assistant
What you'll notice
- Nothing runs against a target until you create an authorization file and mark it granted
- It wants to build a local list of which security tools are installed on your machine
- Strong, insistent wording that tells the assistant to act, not just say it understood
- Offensive techniques are in scope: breaking app protections, evading security software, extracting credentials
What you need
- Claude Code, Codex, Cursor, OpenCode, Kiro, Cline and 1 more
- Free, MIT license
- Clone the project, then run one tool-check command for your system
- No account or key is required. Some tools it can reach (IDA Pro, JEB, Binary Ninja) are paid and you install them yourself; it never downloads commercial software.
Words on this page
- Skill
- A set of written instructions your AI assistant follows. Installing one is like giving it a playbook.
- Skill pack
- Several skills in one GitHub repository, installed together.
- MCP
- A standard way to connect an AI assistant to outside tools and data.
| Repository | zhaoxuya520/reverse-skill |
|---|---|
| GitHub stars | 45,064 |
| Skills | 89 (89 SKILL.md in the repo, 46 in skills/) · 8 with scripts |
| Category | Research and science |
| License | MIT |
| Note | Reverse engineering and penetration-testing skills for authorized security work only (MIT). |
| Last updated | Nov 14, 2026 · card checked Oct 30, 2026 at commit cab634b |
| Install counts | zhaoxuya520/reverse-skill on skills.sh, Vercel's skills directory, which shows installs and security audits per skill |
zhaoxuya520/reverse-skill popularity over time
What reverse-skill does
- Matches a security task to one specialist module by keyword, from a single routing table
- Makes you set up a per-case authorization file (scope) and blocks action on a target until it says granted
- Reads a local index of installed tools so it uses real paths, and offers to install missing ones (with your approval)
- Records work as a timeline and an Evidence to Finding to Path chain, then can write a report
- {'Covers many target types through separate modules': 'Android, iOS, binaries, .NET, web JS, firmware, malware, pen testing, exploitation, EDR evasion, and more'}
From the pack's SKILL.md files, summarised by AgentGid.
The 3 skills, explained
reverse-skill-router
Reads your task and sends the assistant to the right specialist method
You give
- Your task and the target type (an app, a binary, a web page, a capture)
- Written authorization for the target, entered in a scope file
You get
- The chosen specialist module
- A scope file that gates any action on the target
- A set workflow to follow, an evidence chain, and an optional report
apk-reverse
Unpacks, reads and can repackage an Android app
You give
- An Android app file you are allowed to analyse
- What you are looking for (login, signing, a protection check)
You get
- Unpacked and decompiled code
- Notes on where logic lives
- A repackaged app if you asked for a change
pentest-tools
Runs scanning and web-testing tools against a target you are allowed to test
You give
- A target that is inside your granted scope
- What to check (open ports, web issues, weak passwords)
You get
- Scan output routed through the right tool
- Findings tied to evidence
See it in action
When to reach for it
| You want | Use |
|---|---|
| Pick the right method for a security task | plain language, or run skills/scripts/master-route.sh --hint "<task>" |
| Set up authorization before touching a target | skills/scripts/case-init.sh, then grant in the scope file |
| See which security tools are installed | skills/scripts/refresh-tool-index.sh (refresh-tool-index.ps1 on Windows) |
Skills in zhaoxuya520/reverse-skill
| Skill | In plain words | Changes files? | What it does (author) |
|---|---|---|---|
| reverse-skill-router | Reads your task and sends the assistant to the right specialist method | Unclear | Routes reverse engineering, exploitation, penetration testing, malware, mobile, firmware, browser automation, documentation, and security tasks to the appropriate specialist skill. Use when a task spans modules or the correct reverse-skill entrypoint is unclear. has scriptsnpx skills add zhaoxuya520/reverse-skill --skill reverse-skill-router |
| api-security | — | — | Use for authorized security assessment of REST, GraphQL, WebSocket, or SOAP APIs, including discovery, authentication, authorization, rate-limit, and CI/CD testing.npx skills add zhaoxuya520/reverse-skill --skill api-security |
| apk-reverse | Unpacks, reads and can repackage an Android app | Yes | 在 CLI 环境下做 Android APK 逆向时使用。适用于 APK 解包、Java 反编译、smali 修改、重打包、Frida 动态 Hook,以及按需切换到 so/native 分析。优先使用本机已安装的 jadx、apktool、frida、adb、ida-reverse、radare2。 has scriptsnpx skills add zhaoxuya520/reverse-skill --skill apk-reverse |
| attack-chain | — | — | Use for authorized multi-stage attack-path planning and orchestration when a task spans reconnaissance, initial access, privilege escalation, lateral movement, or impact assessment. Route single-stage tasks directly to their specialist skill.npx skills add zhaoxuya520/reverse-skill --skill attack-chain |
| binary-diff | — | — | 跨版本符号迁移与二进制差分。当你有旧版本的符号/逆向结果,需要快速迁移到新版本时使用。 适用场景:内核缺 PDB 用旧版符号推导、程序更新后批量迁移函数名、应用更新后快速定位新偏移。 核心方法:用 LLM 做结构化差异比对,程序化输入输出,成本极低(200 函数 ~1 元)。 触发关键词:符号迁移、bindiff、跨版本、PDB 缺失、函数偏移迁移、symbol migration、binary diff、版本对比。npx skills add zhaoxuya520/reverse-skill --skill binary-diff |
| binary-ninja-reverse | — | — | Use for authorized binary analysis in Binary Ninja, including HLIL/MLIL/LLIL inspection, strings/imports/exports, cross-references, types, patch review, Python API automation, and optional Binary Ninja MCP or localhost HTTP integration.npx skills add zhaoxuya520/reverse-skill --skill binary-ninja-reverse |
| browser-automation | — | — | 统一自动化入口。覆盖浏览器自动化(Playwright)和 Windows 桌面应用自动化(OpenReverse)。 浏览器场景:打开网页、点击、填表、爬取、截图、自动化登录、渗透页面交互。 桌面场景:操作 IDA/x64dbg 等 GUI 工具、Windows UI Automation、视觉驱动交互、桌面应用网络抓包。 触发关键词:浏览器自动化、桌面自动化、打开网页、填表、爬取、截图、自动化登录、Playwright、agent-browser、headless、OpenReverse、UIA、CUA、桌面操作、Windows 自动化。 has scriptsnpx skills add zhaoxuya520/reverse-skill --skill browser-automation |
| browser-extension-reverse | — | — | Use for authorized reverse engineering of browser extensions (Chrome/Firefox) including manifest analysis, background workers, and extension-based credential or traffic logic recovery.npx skills add zhaoxuya520/reverse-skill --skill browser-extension-reverse |
| case-review | Checks a finished case for a complete, traceable evidence chain | No | Reviews a reverse-skill case package for scope readiness, Evidence to Finding to Path traceability, work item coverage, timeline references, and optional artifact hash integrity before report handoff. has scriptsnpx skills add zhaoxuya520/reverse-skill --skill case-review |
| cloud-k8s | — | — | Use for authorized cloud, container, and Kubernetes security assessment including metadata SSRF, IAM misconfig, container escape paths, and cluster RBAC review.npx skills add zhaoxuya520/reverse-skill --skill cloud-k8s |
| code-audit | — | — | Use for authorized source-code security review and SAST workflows including Semgrep, CodeQL patterns, dangerous API hunting, and fix verification.npx skills add zhaoxuya520/reverse-skill --skill code-audit |
| ctf-sandbox | — | — | Thin PRIMARY for CTF / AWD / 靶场 multi-type orchestration. Hands off to the sidecar CTF-Sandbox-Orchestrator. Use when the user says CTF, AWD, 靶场, or 比赛题 and no more specific pwn/APK/IDA route already won.npx skills add zhaoxuya520/reverse-skill --skill ctf-sandbox |
| database-security | — | — | Use for authorized database security assessment covering PostgreSQL/MySQL/MSSQL/Mongo/Redis exposure, authz, UDF/command paths, and misconfiguration review.npx skills add zhaoxuya520/reverse-skill --skill database-security |
| diagram-generator | — | — | generate, refine, validate, and render diagrams from natural language, notes, code snippets, schemas, tables, or existing diagram source. use for flowcharts, swimlanes, sequence diagrams, state diagrams, er diagrams, class diagrams, architecture/c4-style diagrams, dependency graphs, gantt charts,… has scriptsnpx skills add zhaoxuya520/reverse-skill --skill diagram-generator |
| digital-forensics | — | — | Use for authorized digital forensics including memory dumps, disk timelines, PCAP investigation, artifact triage, and IR evidence preservation.npx skills add zhaoxuya520/reverse-skill --skill digital-forensics |
| docs-generator | — | — | Creates task-oriented technical documentation with progressive disclosure. Use when writing READMEs, API docs, architecture docs, or markdown documentation. Also use this skill at the END of any completed reverse engineering, penetration testing, CTF, or security analysis task to generate a formal…npx skills add zhaoxuya520/reverse-skill --skill docs-generator |
| dotnet-reverse | — | — | .NET / C# 二进制逆向。当目标是 .NET assembly(PE 头含 CLR、.exe/.dll 托管程序)、C# 编译产物(含 NativeAOT)、红队 Sharp* 工具(Rubeus / SharpHound / SharpHound 等)、.NET 混淆程序(ConfuserEx / SmartAssembly / Babel / Eazfuscator)、.NET loader / info-stealer / 套壳 malware 时使用。优先用 dnSpyEx + de4dot,需要 AI 直接操作时联动 dnSpy MCP。不用于纯 native 二进制(走…npx skills add zhaoxuya520/reverse-skill --skill dotnet-reverse |
| edr-bypass-re | — | — | 逆向防御方实现 → 红队针对性绕过。把 EDR / Defender / AV 的 hook 表、ETW provider、AMSI 实现先逆向出来, 再写针对性的 unhook / 间接 syscall / ETW patch / call stack spoof。对照 MITRE ATT&CK T1562 防御规避。 触发关键词:EDR 绕过、AV bypass、免杀、unhook、direct syscall、indirect syscall、Hell's Gate、Halo's Gate、 Tartarus Gate、ETW patch、AMSI patch、call stack…npx skills add zhaoxuya520/reverse-skill --skill edr-bypass-re |
| email-security | — | — | Use for authorized email security review including phishing analysis, header authentication (SPF/DKIM/DMARC), BEC patterns, and mailbox token abuse research.npx skills add zhaoxuya520/reverse-skill --skill email-security |
| firmware-pentest | — | — | 固件 / IoT 渗透链。从拿到一坨 .bin / .img 开始,闭环走完逆向 → 提取 → 模拟 → 利用。 方法论遵循 OWASP FSTM 九阶段;工具链以 binwalk v3、unblob、EMBA、Firmadyne、AFL++ 为主。 适用场景:路由器/摄像头/智能家居固件审计、固件升级包逆向、IoT CVE 复现、嵌入式 0day 挖掘。 触发关键词:固件、firmware、IoT、binwalk、unblob、UART、JTAG、squashfs、UBI、JFFS2、Firmadyne、QEMU…npx skills add zhaoxuya520/reverse-skill --skill firmware-pentest |
| ghidra-reverse | — | — | Use for free/open reverse engineering with Ghidra (headless or GUI), including decompile, cross-refs, and optional Ghidra MCP workflows when IDA is unavailable.npx skills add zhaoxuya520/reverse-skill --skill ghidra-reverse |
| go-rust-reverse | — | — | Use for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery. has scriptsnpx skills add zhaoxuya520/reverse-skill --skill go-rust-reverse |
| hardware-security | — | — | Use for authorized hardware and embedded interface security research including UART/JTAG discovery, debug pad triage, secure boot overview, and offline firmware extraction support.npx skills add zhaoxuya520/reverse-skill --skill hardware-security |
| ida-reverse | — | — | IDA Pro 逆向分析辅助技能。当用户提到逆向、反编译、分析二进制/PE/ELF/APK/DLL/SO、破解、找密码、漏洞分析、病毒分析、firmware 固件分析,或需要分析 exe/dll/so/elf/macho/sys 等文件时,务必使用此技能。 Ensure to use this skill when the user wants to analyze any binary file, regardless of whether they explicitly mention "IDA" or "reverse engineering". This includes… has scriptsnpx skills add zhaoxuya520/reverse-skill --skill ida-reverse |
| identity-federation | — | — | Use for authorized assessment of federated identity systems including SAML, OIDC, OAuth2 flows, SSO misconfiguration, and token confusion issues.npx skills add zhaoxuya520/reverse-skill --skill identity-federation |
| js-reverse | — | — | 在使用 js-reverse-mcp 做前端 JavaScript 逆向时使用,适用于签名链路定位、页面观察取证、运行时采样、本地补环境复现与证据化输出。优先适配当前环境里的 js-reverse_* 工具,需要更强的浏览器/CDP/Hook 面时联动 jshookmcp。npx skills add zhaoxuya520/reverse-skill --skill js-reverse |
| llm-security | — | — | Use for authorized security assessment of LLM applications and AI agents, including prompt injection, tool abuse, RAG exposure, memory poisoning, and model supply-chain risks.npx skills add zhaoxuya520/reverse-skill --skill llm-security |
| macos-reverse | — | — | Use for authorized macOS and Mach-O reverse engineering including codesign, Objective-C/Swift recovery, endpoint security surfaces, and Apple platform malware analysis.npx skills add zhaoxuya520/reverse-skill --skill macos-reverse |
| malware-analysis | — | — | Use when analyzing suspected malware through static, dynamic, and behavioral techniques, including IOC extraction, YARA or Sigma rules, sandboxing, and anti-analysis behavior.npx skills add zhaoxuya520/reverse-skill --skill malware-analysis |
| mobile-reverse | — | — | Use for authorized Android or iOS application reverse engineering and security testing, including APK or IPA analysis, runtime instrumentation, SSL pinning, and platform protection checks.npx skills add zhaoxuya520/reverse-skill --skill mobile-reverse |
| ot-ics | — | — | Use for authorized OT/ICS security assessment covering Purdue model zoning, PLC/SCADA exposure, industrial protocol discovery, and safe passive-first evaluation.npx skills add zhaoxuya520/reverse-skill --skill ot-ics |
| patch-diff-exploit | — | — | N-day 补丁差分到利用。从厂商发布的补丁里反推漏洞点、写 PoC、做成可用的攻击模块。 适用场景:已知 CVE 编号但只有补丁没有 PoC、SRC/红队需要打击未及时更新的资产、N-day 武器化、Patch Tuesday 跟进。 核心方法:拿 before/after 二进制 → 对齐符号 → 二进制 diff → 看新增的安全检查反推 bug class → 写 PoC 触发漏洞。 触发关键词:N-day、Nday、补丁差分、patch diff、patch tuesday、1day、binary diff 漏洞、bindiff…npx skills add zhaoxuya520/reverse-skill --skill patch-diff-exploit |
| pentest-tools | Runs scanning and web-testing tools against a target you are allowed to test | Unclear | 主动渗透测试工具链。覆盖信息收集、端口扫描、漏洞扫描、Web 渗透、SQL 注入、目录爆破、密码破解等场景。 通过 MCP server(pentestMCP / mcp-security-hub)将 20+ 安全工具暴露给 AI agent。 触发关键词:渗透测试、端口扫描、Nmap、漏洞扫描、Nuclei、SQL 注入、SQLMap、目录爆破、FFUF、密码破解、Hashcat、信息收集、子域名、Web 渗透、ZAP、Burp。npx skills add zhaoxuya520/reverse-skill --skill pentest-tools |
| src-hunter | — | — | 实战 SRC / 众测 / Bug bounty 漏洞挖掘工作流 skill。包含:5 阶段方法论(intake → recon → enum → hunt → report)、19 个攻击类 playbook(SQLi/XSS/RCE/SSRF/IDOR/CSRF/Path Traversal/File Upload/SSTI/XXE/Race/HTTP Smuggling/OAuth/JWT/SAML/GraphQL/Mobile/LLM/DoS)、305 个结构化 payload、263 个 WAF/EDR 绕过变体、2887 份 HackerOne 真实 High/Critical…npx skills add zhaoxuya520/reverse-skill --skill src-hunter |
| protocol-reverse | — | — | Use for authorized reverse engineering of custom binary protocols, Protobuf/gRPC, WebSocket frames, and PCAP-driven protocol recovery.npx skills add zhaoxuya520/reverse-skill --skill protocol-reverse |
| pwn-chain | — | — | 从逆向走到可用利用 (Working Exploit) 的全链路工程化方法。 适用场景:拿到了二进制 + 漏洞点 + 目标环境,需要写出一个能稳定打通的 exploit(不是只能本地复现一下、远程一打就崩的脚本)。 覆盖三大方向:栈溢出 / 堆利用 / 内核 pwn。强调"CTF 本地通 → 真实远程稳定打通"的工程差距:libc 版本错配、堆喷射时序、SMEP/SMAP/KASLR、栈对齐、远程缓冲。 核心工具链:pwntools + GEF/pwndbg + ROPgadget/Ropper + one_gadget + libc-database + qemu-system…npx skills add zhaoxuya520/reverse-skill --skill pwn-chain |
| radare2 | — | — | Use this skill whenever the user wants to analyze binaries with radare2/r2 from the command line, including reverse engineering, disassembly, function analysis, strings/import inspection, patching, binary diffing, hex inspection, or r2 scripting. Also use it when the user mentions… has scriptsnpx skills add zhaoxuya520/reverse-skill --skill radare2 |
| radio-sdr | — | — | Use for authorized RF/SDR security research including signal identification, replay feasibility study in shielded labs, and wireless protocol analysis outside classic Wi-Fi.npx skills add zhaoxuya520/reverse-skill --skill radio-sdr |
| reverse-engineering | — | — | Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis…npx skills add zhaoxuya520/reverse-skill --skill reverse-engineering |
| dsl-vm-reverse | — | — | Reverse JavaScript-based custom DSL/VM interpreters, non-standard WASM-like runtimes, and risk-control engines. Use when analyzing IIFE or switch-based opcode dispatchers, extracting instruction tables, recovering bytecode semantics, capturing VM state at runtime, or reconstructing execution flow.npx skills add zhaoxuya520/reverse-skill --skill dsl-vm-reverse |
| supply-chain-security | — | — | Use for software supply-chain security assessment covering SBOM, SCA, CI/CD pipelines, container images, build integrity, dependency provenance, and vulnerability reachability.npx skills add zhaoxuya520/reverse-skill --skill supply-chain-security |
| thick-client | — | — | Use for authorized security testing of desktop thick clients including local storage, update channels, IPC, traffic, and client-side trust boundaries.npx skills add zhaoxuya520/reverse-skill --skill thick-client |
| threat-hunting | — | — | Use for blue-team threat hunting, detection engineering with Sigma/YARA, SIEM query design, and incident detection validation.npx skills add zhaoxuya520/reverse-skill --skill threat-hunting |
| threat-intelligence | — | — | Use for authorized OSINT and cyber threat intelligence that enriches IOCs, campaigns, impersonation, scams, or threat actors from public sources. Includes bounded X/Twitter search through Xquik, source preservation, corroboration, and evidence handoff.npx skills add zhaoxuya520/reverse-skill --skill threat-intelligence |
| wifi-wireless | — | — | Use for authorized wireless security assessment including Wi-Fi capture, WPA handshake analysis, rogue AP detection research, and lab-only deauth testing.npx skills add zhaoxuya520/reverse-skill --skill wifi-wireless |
| windows-ad | — | — | Use for authorized Active Directory and Windows identity attacks including Kerberos, AD CS, BloodHound paths, NTLM relay, and domain privilege escalation research.npx skills add zhaoxuya520/reverse-skill --skill windows-ad |
| reverse-skill-adapter | — | — | Use the reverse-skill repository from Codex for authorized reverse engineering, security analysis, CTF, and defensive testing tasks. Requires the reverse-skill repository to be available as the current workspace or an explicitly supplied local path.npx skills add zhaoxuya520/reverse-skill --skill reverse-skill-adapter |
| competition-ad-certificate-abuse | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for AD CS, certificate templates, enrollment rights, EKUs, SAN controls, PKINIT, certificate mapping, and cert-based privilege paths. Use when the user asks about ESC-style abuse, certificate templates, enrollment agents,…npx skills add zhaoxuya520/reverse-skill --skill competition-ad-certificate-abuse |
| competition-agent-cloud | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for AI-agent, prompt-injection, MCP or toolchain, cloud, container, CI/CD, and supply-chain challenges. Use when the user asks to analyze prompt-to-tool flows, retrieval poisoning, mounted secrets, deployment drift,…npx skills add zhaoxuya520/reverse-skill --skill competition-agent-cloud |
| competition-android-hooking | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Android APK hooking, Frida tracing, request-signing recovery, SSL pinning bypass, JNI boundary inspection, and app trust-boundary analysis. Use when the user asks to hook an APK, inspect signer logic, trace Java or…npx skills add zhaoxuya520/reverse-skill --skill competition-android-hooking |
| competition-browser-persistence | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for browser cookies, localStorage, sessionStorage, IndexedDB, Cache Storage, service workers, offline caches, and client-side session persistence. Use when the user asks to inspect browser state, replay cached auth or…npx skills add zhaoxuya520/reverse-skill --skill competition-browser-persistence |
| competition-bundle-sourcemap-recovery | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for source maps, build manifests, chunk registries, emitted bundles, obfuscated loader flow, and frontend runtime recovery. Use when the user asks to reconstruct served JavaScript structure, inspect source maps or chunk…npx skills add zhaoxuya520/reverse-skill --skill competition-bundle-sourcemap-recovery |
| competition-cloud-metadata-path | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for cloud metadata services, instance identity, workload identity, link-local credential paths, role assumption, and metadata-to-privilege trust edges. Use when the user asks to inspect metadata-service access, instance…npx skills add zhaoxuya520/reverse-skill --skill competition-cloud-metadata-path |
| competition-container-runtime | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for live container runtime analysis, mounted secrets, sidecars, namespaces, init containers, entrypoint drift, and route-to-container resolution. Use when the user asks why a live container differs from manifests, where a…npx skills add zhaoxuya520/reverse-skill --skill competition-container-runtime |
| competition-crypto-mobile | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for crypto, encoding, steganography, APK, IPA, and mobile trust-boundary challenges. Use when the user asks to decode a blob, recover a transform chain or key, inspect hidden media payloads, hook an APK or IPA signer,…npx skills add zhaoxuya520/reverse-skill --skill competition-crypto-mobile |
| competition-custom-protocol-replay | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for custom binary or text protocol recovery, handshake reconstruction, framing, sequence control, checksums, stateful replay, and accepted-session reproduction. Use when the user asks to decode an unknown protocol,…npx skills add zhaoxuya520/reverse-skill --skill competition-custom-protocol-replay |
| competition-dpapi-credential-chain | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for DPAPI masterkeys, vault blobs, browser credential stores, protected secrets, domain backup keys, and secret-to-acceptance replay chains. Use when the user asks to inspect DPAPI blobs or masterkeys, recover browser or…npx skills add zhaoxuya520/reverse-skill --skill competition-dpapi-credential-chain |
| competition-file-parser-chain | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for file uploads, imports, previews, archive extraction, format conversion, parser invocation, and deserialization chains. Use when the user asks to inspect an upload or import path, trace archive extraction, preview or…npx skills add zhaoxuya520/reverse-skill --skill competition-file-parser-chain |
| competition-firmware-layout | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for firmware images, partition tables, boot chains, update packages, extracted filesystems, embedded configs, and device-facing trust boundaries. Use when the user asks to unpack firmware, map partition layout, inspect…npx skills add zhaoxuya520/reverse-skill --skill competition-firmware-layout |
| competition-forensic-timeline | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for DFIR chronology, cross-artifact correlation, persistence chains, and incident timeline reconstruction. Use when the user asks to build a forensic timeline, correlate EVTX, PCAP, registry, disk, memory, mailbox, or…npx skills add zhaoxuya520/reverse-skill --skill competition-forensic-timeline |
| competition-graphql-rpc-drift | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for GraphQL schemas, persisted queries, RPC manifests, generated clients, OpenAPI drift, hidden operations, and contract-to-handler mismatches. Use when the user asks to inspect GraphQL or RPC requests, compare client…npx skills add zhaoxuya520/reverse-skill --skill competition-graphql-rpc-drift |
| competition-identity-windows | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Active Directory, Kerberos, LDAP, OAuth, enterprise messaging, Windows host forensics, credential material, and lateral-movement challenges. Use when the user asks to trace tickets or tokens, inspect mailbox rules,…npx skills add zhaoxuya520/reverse-skill --skill competition-identity-windows |
| competition-ios-runtime | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for IPA runtime analysis, Frida hooks, Objective-C or Swift method tracing, Keychain inspection, SSL pinning bypass, URL scheme handling, and iOS request-signing recovery. Use when the user asks to hook an IPA, trace…npx skills add zhaoxuya520/reverse-skill --skill competition-ios-runtime |
| competition-jwt-claim-confusion | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for JWT, JWS, and JWE validation paths, header parsing, key selection, claim acceptance, audience and issuer checks, role derivation, and token-to-identity confusion bugs. Use when the user asks to inspect JWT headers or…npx skills add zhaoxuya520/reverse-skill --skill competition-jwt-claim-confusion |
| competition-k8s-control-plane | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kubernetes API analysis, service-account trust, RBAC edges, admission and controller behavior, cluster secrets, workload mutation, and namespace-scoped drift. Use when the user asks to inspect kube API permissions,…npx skills add zhaoxuya520/reverse-skill --skill competition-k8s-control-plane |
| competition-kerberos-delegation | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kerberos delegation, SPN trust edges, S4U abuse, RBCD, constrained or unconstrained delegation, and service-ticket acceptance. Use when the user asks about constrained delegation, unconstrained delegation, RBCD, S4U,…npx skills add zhaoxuya520/reverse-skill --skill competition-kerberos-delegation |
| competition-kernel-container-escape | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for kernel attack surface, namespace and cgroup boundaries, container isolation assumptions, syscall paths, and escape primitive verification. Use when the user asks to analyze container-to-host escape paths, kernel…npx skills add zhaoxuya520/reverse-skill --skill competition-kernel-container-escape |
| competition-linux-credential-pivot | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Linux credential artifacts, service tokens, SSH material, cloud and container secrets, socket-level trust, and host-to-host pivot chains. Use when the user asks to trace Linux auth artifacts, accepted token or key…npx skills add zhaoxuya520/reverse-skill --skill competition-linux-credential-pivot |
| competition-lsass-ticket-material | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for LSASS-resident secrets, Windows logon sessions, Kerberos ticket caches, DPAPI-backed material, SSP artifacts, and replayable credential extraction. Use when the user asks to inspect LSASS memory, recover tickets or…npx skills add zhaoxuya520/reverse-skill --skill competition-lsass-ticket-material |
| competition-mailbox-abuse | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for enterprise mail abuse, OAuth consent, inbox or forwarding rules, transport rules, shared mailbox access, phishing chains, and token-to-mailbox side effects. Use when the user asks to trace mailbox rules, OAuth consent…npx skills add zhaoxuya520/reverse-skill --skill competition-mailbox-abuse |
| competition-malware-config | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for malware configuration recovery, staged payload boundaries, beacon parameter extraction, and IOC decoding. Use when the user asks to recover a malware config, decode C2 or beacon fields, unpack staged payloads, extract…npx skills add zhaoxuya520/reverse-skill --skill competition-malware-config |
| competition-oauth-oidc-chain | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for OAuth, OIDC, redirect flows, state or nonce handling, PKCE, token exchange, refresh logic, claim mapping, and accepted login paths. Use when the user asks to trace redirects, callback parameters, scopes, state, nonce,…npx skills add zhaoxuya520/reverse-skill --skill competition-oauth-oidc-chain |
| competition-pcap-protocol | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for packet capture analysis, session reconstruction, application-protocol decoding, stream reassembly, beacon timing, and packet-to-process correlation. Use when the user asks to analyze a PCAP, rebuild TCP or UDP…npx skills add zhaoxuya520/reverse-skill --skill competition-pcap-protocol |
| competition-prompt-injection | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for prompt-injection, retrieval poisoning, memory contamination, planner drift, MCP or tool-boundary abuse, and agent exfiltration challenges. Use when the user asks to analyze prompt injection, retrieval poisoning,…npx skills add zhaoxuya520/reverse-skill --skill competition-prompt-injection |
| competition-queue-worker-drift | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for queues, async workers, cron jobs, delayed tasks, retry behavior, worker-only config drift, and payload-to-side-effect chains. Use when the user asks to trace a queue payload, inspect async job execution, explain…npx skills add zhaoxuya520/reverse-skill --skill competition-queue-worker-drift |
| competition-race-condition-state-drift | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for race windows, ordering bugs, idempotency failures, lock gaps, concurrent worker drift, and state inconsistencies that produce decisive effects. Use when the user asks to reproduce timing-sensitive bugs, concurrent…npx skills add zhaoxuya520/reverse-skill --skill competition-race-condition-state-drift |
| competition-relay-coercion-chain | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for forced-auth coercion, relay chains, target selection, NTLM or related acceptance paths, and coercion-to-privilege transitions. Use when the user asks to trace a coercion primitive, follow a relay path, analyze forced…npx skills add zhaoxuya520/reverse-skill --skill competition-relay-coercion-chain |
| competition-request-normalization-smuggling | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for parser differentials, HTTP normalization gaps, ambiguous headers, path decoding drift, transfer-framing mismatches, and request smuggling routes. Use when the user asks to trace proxy and backend parse differences,…npx skills add zhaoxuya520/reverse-skill --skill competition-request-normalization-smuggling |
| competition-reverse-pwn | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for reverse engineering, malware, DFIR, firmware, pwnable, and native exploit challenges. Use when the user asks to reverse a binary, unpack a sample, inspect a memory dump or PCAP, recover malware behavior, debug a…npx skills add zhaoxuya520/reverse-skill --skill competition-reverse-pwn |
| competition-runtime-routing | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for reverse proxies, Host headers, forwarded headers, vhost routing, websocket upgrades, path-prefix rewriting, base-URL derivation, and multi-node route resolution. Use when the user asks which host or container serves a…npx skills add zhaoxuya520/reverse-skill --skill competition-runtime-routing |
| competition-ssrf-metadata-pivot | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for SSRF reachability, internal route probing, metadata-service access, credential pivoting, and token-to-accepted-privilege chains. Use when the user asks to trace SSRF sources, internal hosts, metadata endpoints,…npx skills add zhaoxuya520/reverse-skill --skill competition-ssrf-metadata-pivot |
| competition-stego-media | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for image, audio, video, document, and container steganography. Use when the user asks to inspect metadata, alpha or palette channels, LSBs, thumbnails, appended trailers, QR fragments, transcoding artifacts, or recover a…npx skills add zhaoxuya520/reverse-skill --skill competition-stego-media |
| competition-supply-chain | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for CI/CD, registry, dependency drift, artifact provenance, image build, release pipeline, and runtime consumer challenges. Use when the user asks to trace dependency drift, registry pulls, malicious packages, build or…npx skills add zhaoxuya520/reverse-skill --skill competition-supply-chain |
| competition-template-render-path | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for SSR, template rendering, route loaders, hydration payloads, server-client render boundaries, and template-to-handler enforcement gaps. Use when the user asks to inspect SSR or template routes, trace render context or…npx skills add zhaoxuya520/reverse-skill --skill competition-template-render-path |
| competition-web-runtime | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for CTF web, API, SSR, frontend, queue-backed app, and routing challenges. Use when the user asks to inspect a site or API, follow real browser requests, debug auth or session flow, trace uploads or workers, find hidden…npx skills add zhaoxuya520/reverse-skill --skill competition-web-runtime |
| competition-websocket-runtime | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for WebSocket and SSE handshakes, auth material, subscription state, realtime message schemas, reconnect behavior, and frame-driven runtime effects. Use when the user asks to inspect a WebSocket or SSE handshake, decode…npx skills add zhaoxuya520/reverse-skill --skill competition-websocket-runtime |
| competition-windows-pivot | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for Kerberos, WinRM, SMB, RDP, Windows credential material, replayable tickets, delegation edges, and host-to-host pivot chains. Use when the user asks to replay Kerberos material, trace a WinRM, SMB, or RDP pivot,…npx skills add zhaoxuya520/reverse-skill --skill competition-windows-pivot |
| competition-zip-archive | — | — | Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for ZIP and PKZIP archive challenges, legacy ZipCrypto identification, known-plaintext recovery with bkcrack, key-based decryption, and reproducible extraction. Use when the user asks to solve an encrypted ZIP challenge,…npx skills add zhaoxuya520/reverse-skill --skill competition-zip-archive |
| ctf-sandbox-orchestrator | — | — | Default entrypoint and master ctf-sandbox-orchestrator workflow for CTF, exploit, reverse engineering, DFIR, pwnable, crypto, stego, mobile, AI-agent, cloud, container, Active Directory, Windows-host, and identity challenges. Use first when the user presents challenge infrastructure, binaries,…npx skills add zhaoxuya520/reverse-skill --skill ctf-sandbox-orchestrator |
The author's descriptions come from each skill's SKILL.md; the plain-words column is AgentGid's.
Good to know before you install
- It is offensive tooling, including techniques that defeat protections: evading security software, and later modules that unhook or patch defences.
- It stays read-only on its own: it says that reading its files is not permission to run anything, and a target needs a separate granted authorization.
- It can reach the network and install tools, but the rules say to disclose the exact commands, downloads and network access and get your approval first.
- It carries an "agent obedience" playbook and insistent wording that pushes the assistant to carry out the workflow rather than just reply that it understood.
- The Kali docs contradict each other: the Kali README says the assistant will copy the rules into your assistant's global settings by itself, while the Kali rules file forbids exactly that. Check your global settings after setup.
- Commercial tools are never auto-downloaded: for paid software it only prints guidance and asks you to install it yourself.
Before you start
Works in
- Claude Code: project instructions (CLAUDE.md)
- Codex: plugin (optional adapter) or AGENTS.md
- Cursor, OpenCode: project-instruction or skill mechanism of the client
- Kiro, Cline, Windsurf: rules file
You will need
- Java / JDK: For jadx and apktool
- Node.js 22.12+: For the JS toolchain and MCP servers
- Python 3.x: For Frida and helper scripts
- Homebrew (macOS): The bootstrap installs tools on macOS through Homebrew
- Paid licenses for IDA Pro, JEB or Binary Ninja (optional): Commercial tools are never auto-downloaded; you install them with your own license
Steps only you can do
- Approve the setup plan (exact commands, file writes, downloads, network access) before the first script runs (README_AI.md (section 0, Consent-Gated Setup))
Then: The assistant runs only the approved commands, starting with the tool-index refresh - Grant written authorization for each target in the case's scope.md (auth.status granted plus a network profile) (RULES.md (Activated task hot path) and skills/scripts/case-init.sh)
Then: The assistant may act on the target inside that scope - Buy and install commercial tools yourself (IDA Pro, JEB, Binary Ninja) if a task needs them (skills/scripts/bootstrap-manifest.json)
Then: The assistant refreshes the tool index and uses the installed paths - Enter your sudo password or install Homebrew when an approved bootstrap install needs it (skills/scripts/bootstrap-reverse.sh)
Then: The bootstrap installs the approved package - Complete the Xquik OAuth sign-in or provide XQUIK_API_KEY in your environment (threat-intelligence module only) (skills/threat-intelligence/SKILL.md)
Then: The assistant can search public X posts for indicators
Mistakes to avoid
Name a target in the chat and expect the assistant to start working on it
Run case-init for the task, then set auth.status to granted with a network profile in the case's scope.md
Naming a target does not count as authorization; action on a target stays blocked until scope.md says grantedExpect skills/tool-index.md to be there right after cloning
Approve and run the refresh-tool-index command for your system first
The tool list is generated per machine and is not part of the cloneRun the bootstrap script to install every tool it knows about
Install only the tools the current task needs and that the tool list marks as missing, after approving the exact commands
The rules limit bootstrap to tools that are both needed and missingLet the assistant copy the package rules into your client's global settings (as the Kali README suggests)
Keep the rules inside the project; change global client settings only for a client you pick and a change you approve
The main rules forbid copying repository text into global client configuration without explicit approvalTreat the whole repository as MIT when you copy or ship parts of it
Check the folder you copy; CTF-Sandbox-Orchestrator is GPLv3 and outside tools keep their own licenses
The README lists a GPLv3 folder and third-party tools under their own licenses
Which one to pick
| If you need | Pick |
|---|---|
| You want one router that covers reverse engineering, pentest, malware, firmware and CTF with an authorization gate per case | This pack |
| You only need skills for solving CTF challenges (web, pwn, crypto, reverse, forensics) | ljagiello/ctf-skills |
| You want security research, vulnerability detection and code audit workflows | trailofbits/skills |
| You want web recon and bug-hunting checks (CORS, XSS, SQLi, SSRF, subdomain takeover) | uphiago/recon-skills |
Works well with
- claude-code: The repository ships a CLAUDE.md that loads its routing order as project instructions
- openai-codex: An optional Codex adapter plugin delegates to the same routing core
- pwntools: The pwn-chain module builds its exploit templates on pwntools
- yara-python: The malware-analysis module uses YARA rules through yara-python
May I use it like this?
| Use | Answer | Condition |
|---|---|---|
| In a commercial app | With conditions | MIT for the core; CTF-Sandbox-Orchestrator is GPLv3 and outside tools keep their own licenses |
| Passing the files on | With conditions | MIT files: keep the copyright and permission notice; the CTF-Sandbox-Orchestrator folder is GPLv3 |
| Shipped inside your app | With conditions | MIT parts with the notice; bundling CTF-Sandbox-Orchestrator brings GPLv3 terms |
| Work for clients | With conditions | MIT allows it; only against systems you are authorized to test, and third-party tools follow their own licenses |
What leaves your machine
- Download requests for tools and release lookups (tool names and versions, no case data) → api.github.com and each tool's official download source, Only when you approve a bootstrap install of a missing tool. Opt out: Install the tools yourself and only run the tool-index refresh
- Search queries for indicators (domains, hashes, campaign names) → Xquik, a third-party service for public X data, Only when you use the threat-intelligence module with Xquik connected. Opt out: Do not connect Xquik; use other sources
- Sample hashes or files looked up for malware verdicts → VirusTotal, MalwareBazaar or Triage, When the malware-analysis workflow runs its online lookups. Opt out: Tell the assistant to stay offline and use the offline-sample profile
- Scan and test traffic (ports, web requests, password attempts) → The target hosts in your granted scope, When the pentest modules act on a target after scope is granted. Opt out: Keep the case offline or do not grant network scope
Install reverse-skill
Official commands from the repository
git clone https://github.com/zhaoxuya520/reverse-skill.git bash skills/scripts/refresh-tool-index.sh
On Windows run skills/scripts/refresh-tool-index.ps1 instead; on Kali run kali/scripts/refresh-tool-index.sh. Then load the folder through your assistant's own project-instruction or skill mechanism.
Remove: Delete the cloned folder.
An optional Codex adapter lives in plugins/reverse-skill/; it delegates to the same routing core and registers no servers on its own.
Or with the open-source skills CLI: npx skills add zhaoxuya520/reverse-skill. Skills are instructions your agent follows: read them before installing.
What it installs and runs on your machine
Read in the code at commit cab634b, Oct 30, 2026
| When | What happens |
|---|---|
| First run | A script scans your machine for installed security tools and writes a local tool-index file. |
| Each task | A router script reads the routing table and picks the specialist module for the task. |
| Before any target action | A case-init script writes a per-case scope file; action on the target is blocked until it is marked granted. |
| Missing tool | After you approve, a bootstrap script downloads and installs a tool from its official source; some entries query GitHub releases over the network. Commercial tools are never auto-downloaded. |
| Markdown playbooks | Reference and routing documents. Reading them runs nothing. |
The author's numbers, as reported
AgentGid did not run these tests
- 44 routing rules, 175 benchmark cases and 45 tracked skill modules. Source
Quick answers
- Is it free?
- Yes. The core is MIT; the CTF sandbox folder is GPLv3 (see license checks). Some tools it can use are paid and you install them yourself.
- Do I need an account or key?
- No account or key is required to use the router itself.
- Will it attack something on its own?
- No. It stays read-only until you activate it, and a target stays blocked until you grant authorization in a scope file.
- Is this only for systems I am allowed to test?
- Yes. The project says unauthorized use against systems without permission is strictly prohibited.
- Does it include techniques that bypass protections?
- Yes. Modules cover evading security software (EDR/AV), plus bypassing app checks such as root detection and certificate pinning.
Checked by AgentGid on Oct 30, 2026 against commit cab634b of the pack's own files. agent.md for AI agents · Report a mistake
More research and science skill packs
| # | Skill pack | Skills | GitHub stars | Updated |
|---|---|---|---|---|
| 1 |
K-Dense-AI/scientific-agent-skills A library of 177 science skills for your AI assistant, made by the company K-Dense. Each one teaches the assistant one research t…
|
177 | 58.1K | 2026-11-16 |
| 2 |
Yuan1z0825/nature-skills A box of 22 research helpers for your AI assistant, built around Nature-style papers. It can polish or draft manuscript text, run…
|
24 | 54.5K | 2026-11-22 |
| 3 |
Orchestra-Research/AI-Research-SKILLs A library of 98 skills for AI research, made by the company Orchestra Research. Most skills teach your assistant one machine lear…
|
98 | 14.7K | 2026-10-11 |
| 4 |
HKUSTDial/Supervisor-Skills 将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿,你的 AI 科研副导师。
|
12 | 13.2K | 2026-11-21 |
| 5 |
trailofbits/skills Trail of Bits skills for security research, vulnerability detection, and audit workflows
|
99 | 8,343 | 2026-11-21 |
| 6 |
DenisSergeevitch/ex-ussr-kinship-research Evidence-first genealogy skill for AI agents (Codex, Claude Code): church books, civil, military, deportation and repression reco…
|
1 | 2,724 | 2026-11-21 |