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 liuxinye23/CyberStrikeAI --skill ctf-skillsgit clone --depth 1 https://github.com/liuxinye23/CyberStrikeAIWrote 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/liuxinye23/cyberstrikeai/ctf-skills)<a href="https://agentmods.dev/skills/liuxinye23/cyberstrikeai/ctf-skills"><img src="https://agentmods.dev/badge/skills/liuxinye23/cyberstrikeai/ctf-skills/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/liuxinye23/cyberstrikeai/ctf-skills"><img src="https://agentmods.dev/badge/skills/liuxinye23/cyberstrikeai/ctf-skills.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00047 | $0.01503 |
| Opus 5 | $0.00023 | $0.00751 |
| Sonnet 5 | $0.00009 | $0.00301 |
| Haiku 4.5 | $0.00005 | $0.00150 |
Grade A, and why
ctf-skills scanned grade A with 0 findings 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 10d 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.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
CTF 通用解题技能
何时使用
当用户明确提到 CTF、flag、题目附件、靶题、题解、远程 challenge、Pwn / Reverse / Crypto / Web / Forensics / Misc 分类,或给出一个不确定类别的题目样本时,优先使用本技能。
本技能的职责不是直接替代专项方法,而是先把题目分流到正确方向,并给出稳定的首轮工作流。
快速分流
- 先识别输入形态:URL、端口、压缩包、二进制、脚本、图片、音频、流量包、内存/磁盘镜像、源码、加密文本。
- 再识别主要题型:
- Web:HTTP 入口、表单、JWT、模板、上传、接口、前端逻辑
- Crypto:密文、签名、哈希、随机数、数论、编码与协议细节
- Pwn:ELF、崩溃、远程交互、栈堆格式化字符串、沙箱逃逸
- Reverse:二进制、APK、WASM、壳/混淆、虚拟机、校验逻辑
- Forensics:图片、PDF、PCAP、内存、日志、注册表、磁盘、元数据
- Misc:编码谜题、pyjail、bashjail、二维码、逻辑题、混合题
- 如果题型不清晰,先做最轻量的三步:
- 文件类型与字符串
- 元数据与结构
- 只读网络或入口探测
首轮工作流
通用 triage
- 明确目标:拿 flag、拿 shell、恢复明文、绕过校验、找到隐藏数据。
- 保存原始样本与题目说明,不要一开始就覆盖文件。
- 对附件记录文件名、大小、类型、压缩层级、可执行性和外部依赖。
Web 题
- 先枚举入口、参数、身份态、调试路径和静态资源。
- 关注模板注入、鉴权缺陷、文件读写、接口参数、前端暗藏逻辑。
- 常用起手工具:
http-framework-test、ffuf、sqlmap、nuclei。
Crypto 题
- 先分清是编码、古典、对称、非对称、签名、哈希还是随机数问题。
- 把题目里的常量、密文格式、块长、模数、指数、nonce、IV、已知明文整理清楚。
- 避免在题型未判明前盲跑暴力。
Pwn 题
- 先确认架构、保护、输入面、崩溃点、远程交互方式。
- 关注
checksec类信息、函数调用链、栈堆对象、格式串与 syscall 面。 - 常用起手工具:
strings、gdb、pwntools、ropper/ROPgadget、one-gadget。
Reverse 题
- 先找入口函数、核心校验、密钥来源、常量表、状态机与反调试。
- 确认是“理解算法”还是“提取硬编码秘密”,不要过早做大规模动态分析。
- 常用起手工具:
strings、ghidra、radare2、objdump。
Forensics 题
- 先做文件指纹、元数据、嵌套结构、时间线、隐藏数据面检查。
- 对镜像和流量保持只读分析,必要时复制工作副本。
- 常用起手工具:
binwalk、exiftool、foremost、volatility3、zsteg。
Misc 题
- 把输入拆成“编码/规则/执行环境/交互限制”四部分。
- 对 pyjail、bashjail、逻辑题、二维码、音频图像混合题,优先找最小突破口。
何时切换方向
- Web:探测结果与业务逻辑严重不符,且 HTTP 面没有更多入口时,回头检查前端脚本或题目附件。
- Crypto:样本更像编码/混淆而非真正密码学时,不要继续按高阶密码方向硬攻。
- Pwn:如果核心难点其实是弄清程序做什么,应切到 reverse。
- Reverse:如果已经拿到清晰漏洞原语,再转到 pwn 完成利用。
- Forensics:如果附件真实本体是脚本/二进制,应及时转到 reverse 或 misc。
证据与输出
- 记录每一步的观察、假设、验证结果和下一步分流理由。
- 题解应包含:
- 输入与题型判断
- 首轮 triage 结果
- 关键突破点
- 复现步骤
- flag 获取过程
约束
- 优先使用轻量、可复现、可解释的路径。
- 没有证据时,不要把题目强行归到复杂题型。
- 当某条路线连续两轮没有产生新信息,就回到分流点重新判断。
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.
- 10d ago First seen · 145 lines · 47 tokens per session scan A bcaff4275639
ctf-skills is a skill published in the GitHub repository liuxinye23/CyberStrikeAI (0 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 1,503 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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…