ctf-pwn

Provides binary exploitation techniques for CTF challenges. Use when you already have a vulnerable native target or service and need to turn memory corruption or low-level primitives into code execution or privilege escalation, such as buffer overflows, format strings, heap bugs, ROP, ret2libc, shellcode, kernel exploitation, seccomp bypass, sandbox escape, or Windows/Linux exploit chains. Do not use it when the main blocker is understanding what the binary does; use reverse engineering first. Do not use it for pure web bugs, disk or packet forensics, or standalone crypto/math challenges.

请帮我安装这个 Agent Skill：https://github.com/ljagiello/ctf-skills/tree/main/ctf-pwn

1. 先读取该目录下的 SKILL.md 和其他文件，检查是否有可疑内容（执行未知脚本、读取密钥、向外发送数据等），用中文告诉我它会做什么、需要哪些权限；
2. 等我确认后，再把整个目录安装到 ~/.claude/skills/ctf-pwn/（如果你不是 Claude Code，安装到你自己约定的 skills 目录）；
3. 安装后告诉我怎么触发它。

git clone --depth 1 --filter=blob:none --sparse https://github.com/ljagiello/ctf-skills.git /tmp/ctf-pwn-src
cd /tmp/ctf-pwn-src && git sparse-checkout set "ctf-pwn"
mkdir -p ~/.claude/skills && cp -r "ctf-pwn" ~/.claude/skills/ctf-pwn

Skill 可以让智能体执行脚本。安装第三方 Skill 前务必看一遍内容，详见「安全」一课。