SKILLS & AGENTS/Skill 与 Agent·CLAUDE-SKILL

ctf-super-hub

asdfgh1445/ctf-super-hub

面向小白用户的 CTF / 逆向 Skills 整合包：自动分流、头脑风暴、教学模式、比赛模式、只提示模式

打开仓库Open repository

怎么装：Install: git clone https://github.com/asdfgh1445/ctf-super-hub.git

02 / 现在的位置02 / Why now

它现在处在什么位置Where it stands right now

首次发现FIRST SEEN

03 OCT 202603 OCT 2026

增长GROWTH

+0.4%+0.4%

826 → 829 stars · 2 个快照826 → 829 stars · 2 snapshots

状态STATUS

持续活跃Active

质量 BQuality B

03 / 它能帮你做什么03 / What it helps you do

它能帮你做成什么What it helps you do

04 / 安装04 / Install

怎么装How to install

GIT-CLONE

$

README 里给出的安装方式。The installation method given in the README.

MANUAL-COPY

$

README 里给出的安装方式。The installation method given in the README.

两种装法选一个即可 —— 上面那条给命令行用户，下面那条给写代码的用户。Pick one of the two — the first is for command-line users, the second for people writing code.

05 / 限制与风险05 / Limits and risk

限制与风险Limits and risk

风险不是警告，是可信度的一部分。以下结论只基于文档静态扫描，我们不会执行项目里的任何代码。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.

限制LIMITS

存在风险Risk found

01需要 API KeyREQUIRES API KEY: 是Yes
02需要本地环境NEEDS LOCAL RUNTIME: 是Yes
03需要 DockerNEEDS DOCKER: 未在文档中发现Not found in the docs
04难度DIFFICULTY: 需要本地环境Needs a local runtime

PROVENANCE · 这些结论的依据是什么Where these conclusions come from

来源 URLSource URL: https://github.com/asdfgh1445/ctf-super-hub
原始数据哈希Raw data hash: 592656a48f042d2a0c0b4215765b3dec
解析时间Parsed at: 2026-10-03T23:15:11.929Z
最后一次验证Last verified: 2026-10-04T08:53:33.891Z
增长测量时间Growth measured: 2026-10-03T23:24:59.911Z
发现查询Discovery queries: focus:token:code:context-window
分类来源Category source: rules
焦点Focus: token (3)

静态扫描STATIC SCAN

01下载未知二进制Downloads an unknown binaryctf-reverse/SKILL.md
```
chmod +x binary       # Make executable
```

02需要系统权限Needs system permissionsstrix-rce/SKILL.md

- Write to `/proc/sys/kernel/core_pattern` or mount host with `--privileged`

03执行 Shell 命令Runs shell commandsctf-ai-ml/SKILL.md
```
allowed-tools: Bash
```
04读写本地文件Reads and writes local filesctf-ai-ml/SKILL.md
```
allowed-tools: Write
```
05读写本地文件Reads and writes local filesctf-ai-ml/SKILL.md
```
allowed-tools: Edit
```
06执行 Shell 命令Runs shell commandsctf-crypto/SKILL.md
```
allowed-tools: Bash
```
07需要系统权限Needs system permissionsctf-forensics/SKILL.md
```
sudo mount -o loop,ro image.dd /mnt/evidence
```

08需要系统权限Needs system permissionsctf-misc/SKILL.md

- [linux-privesc.md](linux-privesc.md) - Sudo wildcard parameter injection (fnmatch), crafted pcap for sudoers.d, monit confcheck process in

09控制浏览器Controls a browserctf-misc/SKILL.md

- [games-and-vms-4.md](games-and-vms-4.md) - Part 4 (2018-era): XSLT as Turing-complete VM, JavaScript MAX_SAFE_INTEGER successor equality,

10读取 API KeyReads an API keyctf-misc/SKILL.md

`COPY (SELECT '') TO PROGRAM 'cmd'` executes OS commands as postgres. `pg_read_file('/path')` reads files. Extract credentials from `pg_base

这里只做静态扫描：读 README、SKILL.md 和依赖清单，不执行代码。没有命中不代表安全。This is static scanning only: we read the README, SKILL.md and dependency list, and never execute code. No findings does not mean safe.

完整解析证据 JSONFull parse evidence JSON

{
  "agents": [
    {
      "agent": "claude-code",
      "evidence": "readme: …ME 下面直接给你 4 种常见装法： - Codex - Claude Code - Gemini CLI - OpenCode 你只需要…"
    },
    {
      "agent": "gemini-cli",
      "evidence": "readme: …见装法： - Codex - Claude Code - Gemini CLI - OpenCode 你只需要照着自己正在用的那个装就行…"
    },
    {
      "agent": "opencode",
      "evidence": "readme: …- Claude Code - Gemini CLI - OpenCode 你只需要照着自己正在用的那个装就行。 **不用四个都装。…"
    }
  ],
  "apiKey": "en use `Authorization: Token $CTF_TOKEN` header for all requests. ```bash expo",
  "docker": null,
  "taxonomy": {
    "scores": {
      "design": 0,
      "ai-tools": 1,
      "dev-tools": 0,
      "indie-web": 0,
      "skill-agent": 7,
      "productivity": 0
    },
    "primary": "skill-agent",
    "secondary": "claude-skill"
  },
  "localRuntime": "ions (example: `-ho --disable-gpu,proxy-server=http://127.0.0.1:8080`). -",
  "skillMdTotal": 35,
  "skillMdErrors": [],
  "treeTruncated": false,
  "categoryScores": {
    "data": 1,
    "agent": 0,
    "media": 0,
    "design": 0,
    "browser": 0,
    "devtool": 0,
    "security": 3,
    "marketing": 0,
    "productivity": 0
  },
  "classification": [
    {
      "signal": "35 SKILL.md with name + description",
      "weight": 0.95
    },
    {
      "signal": "README describes a Claude / Agent Skill",
      "weight": 0.7
    }
  ],
  "scannedSources": [
    "readme",
    "brainstorming/SKILL.md",
    "ctf-ai-ml/SKILL.md",
    "ctf-beginner-hub/SKILL.md",
    "ctf-crypto/SKILL.md",
    "ctf-forensics/SKILL.md",
    "ctf-malware/SKILL.md",
    "ctf-misc/SKILL.md",
    "ctf-osint/SKILL.md",
    "ctf-pwn/SKILL.md",
    "ctf-reverse/SKILL.md",
    "ctf-super-hub/SKILL.md",
    "ctf-web/SKILL.md",
    "ctf-writeup/SKILL.md",
    "solve-challenge/SKILL.md",
    "strix-authentication-jwt/SKILL.md",
    "strix-beginner-hub/SKILL.md",
    "strix-broken-function-level-authorization/SKILL.md",
    "strix-business-logic/SKILL.md",
    "strix-csrf/SKILL.md",
    "strix-ffuf/SKILL.md",
    "strix-httpx/SKILL.md",
    "strix-idor/SKILL.md",
    "strix-information-disclosure/SKILL.md",
    "strix-insecure-file-uploads/SKILL.md",
    "strix-katana/SKILL.md",
    "strix-nuclei/SKILL.md",
    "strix-open-redirect/SKILL.md",
    "strix-path-traversal-lfi-rfi/SKILL.md",
    "strix-quick/SKILL.md",
    "strix-rce/SKILL.md",
    "strix-sql-injection/SKILL.md",
    "strix-sqlmap/SKILL.md",
    "strix-ssrf/SKILL.md",
    "strix-standard/SKILL.md",
    "strix-xss/SKILL.md"
  ],
  "skillMdFetched": 35
}