claude-reverse-skills: Claude Code 逆向工程 skill 集合 (apk/ida/radare2/js) + IDA MCP 接入,跨平台 Linux/Mac/Windows

by haikow · MCP Server · ★ 93

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install claude-reverse-skills

git clone https://github.com/haikow/claude-reverse-skills && cd claude-reverse-skills
git clone https://github.com/haikow/claude-reverse-skills; cd claude-reverse-skills

Taken from the project's README on GitHub. Check the security audit before running it.

Security audit verdict: SAFE · quality 49/100

None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

Quick Facts

Stars93
Forks23
LanguagePowerShell
CategoryMCP Server
Quality Score49/100
Last Updated2026-06-30
Created2026-06-10
Platformsclaude-code, mcp
Est. Tokens~15k

About claude-reverse-skills

claude-reverse-skills 一套面向 Claude Code(及兼容的文件系统型 Agent)的逆向工程 Skill 集合,外加 IDA Pro MCP 的接入说明。跨平台(Linux / macOS / Windows),一条命令装进 。 🙏 来源:核心 Skill 来自 linux.do 论坛 @hisence 大佬的分享 —— 原帖 👉 https://linux.do/t/topic/2142539 。本仓库仅做整理与跨平台适配,致谢原作者(详见文末「许可与致谢」)。 相关资源(备选) 做逆向时,AI(含 Claude Code)有时会因为安全策略对某些操作拒答。 多数情况用本仓库的 skill + 本机工具(jadx / frida / r2 / IDA)就能完成,不必提权。 仅在确认是合理安全研究、却被护栏硬拦住时,可参考: ClawGod —...

Compatible Skills

These tools work well together with claude-reverse-skills for enhanced workflows:

  • ida-agent-bridge — semantic(0.62)+complementary+similar_pop+shared_platform (62%)

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular PowerShell Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools