REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
This repo is a collection of 146 skills
Recon & pentest skill pack. CORS, XSS, SQLi, SSRF, RCE, WordPress, MCP, cloud, subdomain takeover, and more. Field-tested. MIT. Full write-up at hiago.sh如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/uphiago-recon-skills)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 recon-skills | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | uphiago | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 146 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 1,389 | 468,733 | 234,332 | 150,287 | 144,566 |
| 最近代码更新 | 2026年11月7日 | 2026年11月19日 | 2026年4月20日 | 2026年11月18日 | 2026年11月18日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
uphiago 提供的 146 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
Install only the ones you use. Open a skill to see how to install it
This set has 146 skills, too many to install at once: every installed skill’s description loads into every chat, so the AI picks the wrong one more easily. Pick only the ones you use from the list below
Showing 30 of 146 See all on GitHub
Use when protected HTTP routes return 401 or 403.
Use when an API may expose data or privileged operations without authentication.
Map organization IP infrastructure via ASN, CIDR, TLD expansion, and reverse DNS.
Use when classifying a verified web or WordPress behavior and selecting a related validation skill.
No description from the maker
Identify CMS, frameworks, and server technology stacks on live hosts.
Exploit WP CORS credential reflection for data theft.
Use when two or more verified findings may combine into a higher-impact authorized attack path.
Compare recon waves to find NEW, REGRESSED, PERSISTENT findings.
Deep pentest WP: SSRF, plugin CVE, JS mine, port scan chain.
Escape Docker containers to host root via 5 techniques.
DMARC/SPF/DKIM check, email spoofing, SMTP test, and security header analysis
Mine error_log for creds, paths, SQL when leak hunt finds.
Exchange/OWA NTLM AD leak, spray attack when mail subdomain.
No description from the maker
Exploit Flask/Werkzeug debugger exposure for traceback and SECRET leaks.
Find leaked API keys, tokens, and credentials in public GitHub repositories.
Mine GitLab for secrets, CI tokens when subdomain found.
High-precision Google dorks for exposed configs, secrets, and credentials -- real-world validated
Detect hardcoded passwords in HTML forms, JavaScript, and API responses.
Spoof HTTP/2 SETTINGS frames and pseudo-header order per browser profile.
Human-like mouse, keyboard and scroll behavior for behavioral bot bypass.
Attack cameras via RTSP, ONVIF, Axis config when 554 open.
Analyze JS bundles and source maps for hardcoded secrets, API keys, JWTs, and internal endpoints
Decode, forge, brute JWTs when Bearer auth header is seen.
7-phase pentest pipeline from passive recon to exploitation.
Use when starting or restructuring an authorized external web and API assessment.
No description from the maker
Pick sectors, compile targets, batch recon for campaigns.
Use when verified WordPress findings may combine into an authorized path to administrative or server control.
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
开发者未说明 · SKILL.md 形式的 Skill 可用于支持 Agent Skills 的应用,如 Claude Code、Codex 和 Cursor
This repo has 146 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
提问、分享技巧或报告无法使用。按“有帮助”数量排序。