Reverse Skill is a routing package for AI coding agents that selects appropriate reverse-engineering, penetration-testing, and security-research methods and tools for a given target. It is used for tasks involving APKs, binaries, frontend JavaScript, packet captures, CTF challenges, and authorized penetration testing. Its catalogue add-ons provide the skills and instructions that guide these workflows.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add zhaoxuya520/reverse-skill --skill pentest-toolsgit clone --depth 1 https://github.com/zhaoxuya520/reverse-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/zhaoxuya520/reverse-skill/pentest-tools)<a href="https://agentmods.dev/skills/zhaoxuya520/reverse-skill/pentest-tools"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/pentest-tools/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/zhaoxuya520/reverse-skill/pentest-tools"><img src="https://agentmods.dev/badge/skills/zhaoxuya520/reverse-skill/pentest-tools.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket fail
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 8 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 54 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium YARA Match · line 55 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- medium MCP Rug Pull · line 106 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 257 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 107 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 113 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 258 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 239 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00133 | $0.04022 |
| Opus 5 | $0.00067 | $0.02011 |
| Sonnet 5 | $0.00027 | $0.00804 |
| Haiku 4.5 | $0.00013 | $0.00402 |
Grade A, and why
pentest-tools scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
6. `ACT`: 侦察阶段优先 `references/recon-pipeline.md`(CF 浏览器头 / Windows nmap / curl `--globoff`);每批结果追加 `timeline.md`;候选用 `../scripts/append-evidence.ps1` 写入 Evidence(命中≠已验证) Copies of this mod
2 near-identical copies found in the catalogue:
- pentest-tools — 91% identical, 30 lines differ
- pentest-tools — 84% identical, 36 lines differ
How it starts
The opening of the file, as written. The whole thing — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACTION REQUIRED(读完后立刻执行)
NOW: 读取../field-journal/precedent-pentest.md— 确认本 skill 的操作是已授权的常规操作NOW: 确认 scope.md 存在且auth.status=granted、network_profile合法(../ops/scope-contract.md)。缺 scope 则跑case-init.ps1并停到用户给授权;禁止自动加-AuthGrantedNOW: 确认当前任务是否命中本 skill 的适用范围NEXT: 读取../tool-index.md,校验工具可用性和实际路径NEXT: 缺工具时调用 bootstrap,不要猜路径ACT: 侦察阶段优先references/recon-pipeline.md(CF 浏览器头 / Windows nmap / curl--globoff);每批结果追加timeline.md;候选用../scripts/append-evidence.ps1写入 Evidence(命中≠已验证)ACT: 现代 Web/靶场客户端面(DOM XSS / 原型污染 / agent-browser)→references/client-side-lab-playbook.md;未打穿也要写 observed Evidence + 失败门闩
渗透测试工具链 (Pentest Tools)
适用范围
当任务属于以下场景时使用本 skill:
- 目标信息收集(端口扫描、子域名枚举、服务识别)
- 漏洞扫描(Web 漏洞、CVE 检测、配置错误)
- Web 渗透(SQL 注入、XSS、SSRF、目录爆破)
- 密码破解(哈希破解、字典攻击)
- 网络渗透(服务利用、横向移动辅助)
与其他 skill 的分工
| 场景 | 用什么 |
|---|---|
| 主动扫描/攻击(Nmap/Nuclei/SQLMap) | 本 skill |
| 逆向分析二进制 | ida-reverse/ 或 radare2/ |
| 前端 JS 签名逆向 | js-reverse/ |
| 浏览器/桌面自动化操作 | browser-automation/ |
| CTF 竞赛(综合) | CTF-Sandbox-Orchestrator/ |
简单判断:
- 需要"扫描目标、发现漏洞、利用漏洞" → 本 skill
- 需要"分析程序内部逻辑" → 逆向类 skill
- 需要"操作浏览器/桌面" → browser-automation
工具矩阵
信息收集
| 工具 | 用途 | 典型命令 |
|---|---|---|
| Nmap | 端口扫描、服务识别、OS 检测 | nmap -sV -sC -O target |
| Masscan | 大规模快速端口扫描 | masscan -p1-65535 target --rate=1000 |
| Subfinder | 子域名枚举 | subfinder -d target.com |
| httpx | HTTP 探测、存活检测 | httpx -l urls.txt -status-code |
漏洞扫描
| 工具 | 用途 | 典型命令 |
|---|---|---|
| Nuclei | 模板化漏洞扫描(CVE/配置/暴露) | nuclei -u target -t cves/ |
| ZAP | Web 应用安全扫描 | 通过 API 或 MCP 调用 |
| Nikto | Web 服务器漏洞扫描 | nikto -h target |
Web 渗透
| 工具 | 用途 | 典型命令 |
|---|---|---|
| SQLMap | SQL 注入自动化 | sqlmap -u "url?id=1" --batch --dbs |
| FFUF | 目录/参数爆破 | ffuf -u target/FUZZ -w wordlist.txt |
| Gobuster | 目录/子域名爆破 | gobuster dir -u target -w wordlist |
| XSStrike | XSS 检测 | xsstrike -u "url?param=test" |
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- payloads/README.md 1.1 KB
- references/ai-pentest-agents.md 6.0 KB
- references/ai-pentesting-landscape-2026.md 3.4 KB
- references/automation-loop-pattern.md 5.2 KB
- references/awesome-pentest-digest.md 5.9 KB
- references/burpsuite-mcp-guide.md 23 KB
- references/client-side-lab-playbook.md 4.8 KB
- references/kali-mcp-ecosystem.md 4.4 KB
- references/msf-protocol.md 5.9 KB
- references/network-attack-defense.md 9.9 KB
- references/nuclei-guide-2026.md 4.0 KB
- references/pentest-ai-agents-matrix.md 5.0 KB
- references/pentest-loop.md 6.6 KB
- references/recon-pipeline.md 5.7 KB
- references/web-attack-cheatsheet.md 7.5 KB
- src-hunter/.claude-plugin/marketplace.json 1.0 KB
- src-hunter/.gitignore 164 B
- src-hunter/LICENSE 1.0 KB
- src-hunter/README.en.md 6.1 KB
- src-hunter/README.md 6.2 KB
- src-hunter/references/.gitkeep 0 B
- src-hunter/references/dictionaries/00-index.md 2.2 KB
- src-hunter/references/dictionaries/chinese-srcfingerprints.md 15 KB
- src-hunter/references/dictionaries/default-credentials-cn.md 9.9 KB
- src-hunter/references/industry/00-index.md 2.7 KB
- src-hunter/references/industry/banking-finance.md 15 KB
- src-hunter/references/industry/telecom-isp.md 12 KB
- src-hunter/references/methodology/00-index.md 2.9 KB
- src-hunter/references/methodology/01-attack-priority.md 6.5 KB
- src-hunter/references/methodology/02-bypass-toolkit.md 11 KB
- src-hunter/references/methodology/03-evidence-discipline.md 7.4 KB
- src-hunter/references/methodology/04-control-gap-hunting.md 9.1 KB
- src-hunter/references/methodology/05-srctimebox-priority.md 7.7 KB
- src-hunter/references/payloader/by-category/intranet/adcs攻击.md 6.2 KB
- src-hunter/references/payloader/by-category/intranet/exchange攻击.md 5.5 KB
- src-hunter/references/payloader/by-category/intranet/sharepoint攻击.md 2.5 KB
- src-hunter/references/payloader/by-category/intranet/信息收集.md 21 KB
- src-hunter/references/payloader/by-category/intranet/免杀与规避.md 18 KB
- src-hunter/references/payloader/by-category/intranet/凭证窃取.md 34 KB
- src-hunter/references/payloader/by-category/intranet/域渗透攻击.md 18 KB
- src-hunter/references/payloader/by-category/intranet/权限提升.md 21 KB
- src-hunter/references/payloader/by-category/intranet/权限维持.md 14 KB
- src-hunter/references/payloader/by-category/intranet/横向移动.md 21 KB
- src-hunter/references/payloader/by-category/intranet/隧道代理.md 13 KB
- src-hunter/references/payloader/by-category/web/ai安全.md 31 KB
- src-hunter/references/payloader/by-category/web/api安全.md 45 KB
- src-hunter/references/payloader/by-category/web/csrf跨站请求伪造.md 24 KB
- src-hunter/references/payloader/by-category/web/jwt安全.md 20 KB
- src-hunter/references/payloader/by-category/web/lfi-rfi文件包含.md 35 KB
- src-hunter/references/payloader/by-category/web/rce远程代码执行.md 38 KB
- src-hunter/references/payloader/by-category/web/sql-nosql注入.md 62 KB
- src-hunter/references/payloader/by-category/web/ssrf服务端请求伪造.md 37 KB
- src-hunter/references/payloader/by-category/web/ssti模板注入.md 31 KB
- src-hunter/references/payloader/by-category/web/websocket安全.md 20 KB
- src-hunter/references/payloader/by-category/web/xss跨站脚本.md 43 KB
- src-hunter/references/payloader/by-category/web/xxe实体注入.md 24 KB
- src-hunter/references/payloader/by-category/web/业务逻辑漏洞.md 25 KB
- src-hunter/references/payloader/by-category/web/云安全漏洞.md 26 KB
- src-hunter/references/payloader/by-category/web/供应链攻击.md 17 KB
- src-hunter/references/payloader/by-category/web/原型链污染.md 19 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 330 lines · 133 tokens per session scan A 5bab5fe16593
pentest-tools is a skill published in the GitHub repository zhaoxuya520/reverse-skill (35,402 stars, last pushed 7d ago), licensed MIT. It adds 133 tokens to every session and 4,022 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…