Agent skill

Ctf AI ML

CTF AI/ML 攻击技术。当挑战涉及 AI 模型攻击、对抗样本生成、模型提取、Prompt 注入/越狱、LoRA 权重操纵、LLM Token 走私、成员推理攻击、训练数据投毒、神经网络分析时使用。覆盖 FGSM/PGD/C&W 对抗攻击、模型反演、模型权重扰动还原、LLM 工具链劫持、上下文窗口操纵等 AI 安全全链路攻防技术

No licenceAuto-check passedSecurity

Install Ctf AI ML

skills CLI

$ npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install wgpsec/AboutSecurity ctf-ai-ml --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/wgpsec/AboutSecurity.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ctf/ctf-ai-ml .claude/skills/ctf-ai-ml && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "ctf-ai-ml" agent skill from https://github.com/wgpsec/AboutSecurity/tree/master/skills/ctf/ctf-ai-ml into .claude/skills/ctf-ai-ml/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ctf-ai-ml", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/wgpsec/AboutSecurity/tree/master/skills/ctf/ctf-ai-ml

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install wgpsec/AboutSecurity ctf-ai-ml --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wgpsec/AboutSecurity.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ctf/ctf-ai-ml .agents/skills/ctf-ai-ml && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "ctf-ai-ml" agent skill from https://github.com/wgpsec/AboutSecurity/tree/master/skills/ctf/ctf-ai-ml into .agents/skills/ctf-ai-ml/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ctf-ai-ml", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install wgpsec/AboutSecurity ctf-ai-ml --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wgpsec/AboutSecurity.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ctf/ctf-ai-ml .cursor/skills/ctf-ai-ml && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "ctf-ai-ml" agent skill from https://github.com/wgpsec/AboutSecurity/tree/master/skills/ctf/ctf-ai-ml into .cursor/skills/ctf-ai-ml/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ctf-ai-ml", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/wgpsec/AboutSecurity.git --path skills/ctf/ctf-ai-ml

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install wgpsec/AboutSecurity ctf-ai-ml --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wgpsec/AboutSecurity.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ctf/ctf-ai-ml .gemini/skills/ctf-ai-ml && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "ctf-ai-ml" agent skill from https://github.com/wgpsec/AboutSecurity/tree/master/skills/ctf/ctf-ai-ml into .gemini/skills/ctf-ai-ml/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ctf-ai-ml", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install wgpsec/AboutSecurity ctf-ai-ml

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/wgpsec/AboutSecurity.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ctf/ctf-ai-ml .github/skills/ctf-ai-ml && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "ctf-ai-ml" agent skill from https://github.com/wgpsec/AboutSecurity/tree/master/skills/ctf/ctf-ai-ml into .github/skills/ctf-ai-ml/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ctf-ai-ml", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install wgpsec/AboutSecurity ctf-ai-ml --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/wgpsec/AboutSecurity.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ctf/ctf-ai-ml .opencode/skills/ctf-ai-ml && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "ctf-ai-ml" agent skill from https://github.com/wgpsec/AboutSecurity/tree/master/skills/ctf/ctf-ai-ml into .opencode/skills/ctf-ai-ml/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ctf-ai-ml", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: ctf-ai-ml
GitHub stars: 1.8k
Token cost: ~533 tokens
SKILL.md length: 160 words
Files: 4 (incl. references)
Skills in repo: 74
Repo updated: Oct 8, 2026
First seen: Oct 7, 2026
Licence: None found

At a glance

Works in 6 steps: Model weight file (.pt/.safetensors) →… → Image classifier to fool →… → LLM/chatbot target → llm-attacks.md → …
Tasks that involve Capture the flag
SKILL.md covers When to Use, Quick Start, Decision Tree and Pivot Signals
Calls pip and python3

What it does

Ctf AI ML is an agent skill from wgpsec/AboutSecurity. CTF AI/ML 攻击技术。当挑战涉及 AI 模型攻击、对抗样本生成、模型提取、Prompt 注入/越狱、LoRA 权重操纵、LLM Token 走私、成员推理攻击、训练数据投毒、神经网络分析时使用。覆盖 FGSM/PGD/C&W 对抗攻击、模型反演、模型权重扰动还原、LLM 工具链劫持、上下文窗口操纵等 AI 安全全链路攻防技术

Its SKILL.md is about 530 tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `references/adversarial-ml.md`, `references/llm-attacks.md` and `references/model-attacks.md`).

It sits in Security, covering Capture the flag. The repository describes itself as: Everything for pentest. | 渗透测试知识库，以 AI Agent 可执行的格式沉淀安全方法论。

When your agent uses it

Tasks that involve Capture the flag

Example prompts

“/ctf-ai-ml”

Requirements

Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

Model weight file (.pt/.safetensors) → model-attacks.md
Image classifier to fool → adversarial-ml.md
LLM/chatbot target → llm-attacks.md
Pure math/crypto inside ML → Switch to ctf-crypto
Compiled model binary → Switch to ctf-reverse
Python jail wrapped in chatbot → Switch to ctf-misc

What it can do on your machine

Read from SKILL.md and the folder at commit d428372. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- pip
- python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Ctf AI ML loads about 533 tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 44 tokens; SKILL.md has 160 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~44
When it runs · the whole SKILL.md, loaded when a task matches: ~533
With references · SKILL.md plus every file in references/, read only if the agent opens them: ~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 160 words (~533 tokens).

name: ctf-ai-ml
metadata.tags: ai,ml,machine learning,adversarial,FGSM,PGD,model extraction,model inversion,prompt injection,jailbreak,token…
metadata.category: ctf

Read the full SKILL.md on GitHub

Files

SKILL.md and 3 other files (references) in skills/ctf/ctf-ai-ml of wgpsec/AboutSecurity.

SKILL.md
references/adversarial-ml.md
references/llm-attacks.md
references/model-attacks.md

Open the folder on GitHubat commit d428372

Compare with similar skills

Ctf AI ML next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Ctf AI ML compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Ctf AI ML this skillwgpsec/AboutSecurity	1.8k	—	~533	Automated safety check: Pass	None	yesterday
Reverse Flowlingbol088-spec/reverse-flow-skill	940	—	~2.4k	Automated safety check: Pass	MIT	2 mo ago
Ctf Osintljagiello/ctf-skills	3.4k	1 repos	~2.3k	Automated safety check: Notes	MIT	26 days ago
Penetration Flowlingbol088-spec/ReiPenFlow	222	—	~1.8k	Automated safety check: Pass	MIT	2 mo ago
Helloctf SkillProbiusOfficial/Hello-CTF	4.2k	—	~387	Automated safety check: Pass	GPL-3.0	today
Secknowledge SkillPa55w0rd/secknowledge-skill	424	—	~2.7k	Automated safety check: Pass	None	3 mo ago

Similar skills

Reverse Flow
lingbol088-spec/reverse-flow-skill
Guided reverse engineering workflow for binaries, firmware, mobile apps, scripts, document samples, protocol captures, and unknown artifacts.
940 GitHub stars~2.4k tokensUpdated 2 mo ago
SecurityAuto-check passed
Ctf Osint
ljagiello/ctf-skills
Provides open source intelligence techniques for CTF challenges.
3.4k GitHub starsUsed in 1 repo~2.3k tokens
SecurityAuto-check: notes
Penetration Flow
lingbol088-spec/ReiPenFlow
Guided workflow for authorized penetration testing, vulnerability validation, security reporting, CTF/local sandbox reverse engineering, and user-directed vulnerability research.
222 GitHub stars~1.8k tokensUpdated 2 mo ago
SecurityAuto-check passed
Helloctf Skill
ProbiusOfficial/Hello-CTF
Hello CTF 技能树 —— 基于国内 CTF 竞赛体系整理的全方向攻防知识库。当用户在学习 CTF、备战比赛、解赛题（Web / Crypto / Misc / Pwn / Reverse / AI / 云安全 / 数据安全 / 区块链 / 工控 / 物联网 / 应急响应 / 渗透测试）需要定位知识点、查询利用手法或规划学习路线时使用。也适用于按知识域出题、查漏补缺。
4.2k GitHub stars~387 tokensUpdated today
SecurityAuto-check passed
Secknowledge Skill
Pa55w0rd/secknowledge-skill
Web+AI 安全测试知识库。融合 WooYun 88,636 案例 + 先知 L1-L4 方法论 + GAARM 173 风险 + OWASP Top 10 (LLM/ASI/WSTG)。
424 GitHub stars~2.7k tokensUpdated 3 mo ago
SecurityAuto-check passed
Vuln Research
tanweai/xianzhi-research
安全研究元思考方法论 - 从先知社区5600+篇安全文档中提炼的漏洞挖掘方法论框架. An agent skill from tanweai/xianzhi-research.
185 GitHub stars~847 tokensUpdated 8 mo ago
SecurityAuto-check passed

More from wgpsec/AboutSecurity

All 74 skills in this repo

Aboutsecurity Content Ingestion
wgpsec/AboutSecurity
A skill your agent uses whenever the user asks to add, absorb, migrate, port, update, merge, compare, or extract security knowledge into the AboutSecurity repository from any external resource such…
1.8k GitHub stars~1.4k tokensUpdated yesterday
Auto-check passed
Ad Persistence
wgpsec/AboutSecurity
AD 域环境持久化技术。当已获取域管/本地管理员权限、需要建立持久访问以确保重启或密码更改后仍能回到目标环境时使用。覆盖主机级持久化（计划任务/注册表Run/COM劫持/WMI事件订阅/Windows服务/启动文件夹）、域级持久化（Golden Ticket/Silver Ticket/Skeleton…
1.8k GitHub stars~2.3k tokensUpdated yesterday
Auto-check passed
Apt Emulation
wgpsec/AboutSecurity
APT 模拟与情报驱动红队方法论。基于已知 APT 组织的 TTP（MITRE ATT&CK）设计红队行动计划。当需要模拟特定威胁组织、设计高仿真攻击演练、或根据威胁情报制定攻击策略时使用
1.8k GitHub stars~922 tokensUpdated yesterday
Auto-check passed
Argocd Tactics
wgpsec/AboutSecurity
ArgoCD 后渗透方法论：Redis缓存投毒集群接管、SSO认证绕过、未授权API枚举、恶意Application部署、Webhook SSRF、默认凭据利用。
1.8k GitHub stars~510 tokensUpdated yesterday
Auto-check passed
C2 Beacon Analysis
wgpsec/AboutSecurity
C2 Beacon 配置提取与分析。当捕获到 Cobalt Strike/Sliver/Havoc 等 C2 框架的 Beacon 样本、内存 dump、或网络流量时使用。提取 C2 地址、通信协议、Malleable Profile、Watermark 等关键情报。红队视角：了解蓝队如何从 Beacon 提取 IOC 以改进 C2 OPSEC
1.8k GitHub stars~1.2k tokensUpdated yesterday
Auto-check passed
C2 Evasion Methodology
wgpsec/AboutSecurity
C2框架免杀方法论：分析 C2 源码、搜索检测规则(YARA/Sigma/Snort)、逐规则分析、修改源码绕过检测。当遇到 YARA/Sigma/Snort 规则触发告警、beacon/implant 被杀软检测到时使用。第一步：确认 implant/beacon 语言和架构；第二步：搜索对应检测规则并逐规则分析修改
1.8k GitHub stars~557 tokensUpdated yesterday
Auto-check passed

Questions about Ctf AI ML

What does Ctf AI ML do?

When should I use Ctf AI ML?

Ctf AI ML fits situations like: tasks that involve Capture the flag.

How do I install Ctf AI ML in Claude Code?

Run `npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a claude-code`. Or copy the skill folder (skills/ctf/ctf-ai-ml in wgpsec/AboutSecurity) into .claude/skills/ctf-ai-ml in your project. Claude Code loads it when a task matches its description.

How do I install Ctf AI ML in Codex?

Run `npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a codex`. Or copy the skill folder (skills/ctf/ctf-ai-ml in wgpsec/AboutSecurity) into .agents/skills/ctf-ai-ml in your project. Codex loads it when a task matches its description.

Can I use Ctf AI ML in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add wgpsec/AboutSecurity --skill ctf-ai-ml -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ctf-ai-ml, .gemini/skills/ctf-ai-ml, .github/skills/ctf-ai-ml and .opencode/skills/ctf-ai-ml in your project.

What does Ctf AI ML need to run?

Going by SKILL.md and its folder, Ctf AI ML needs the command-line tools its instructions call (pip and python3). Our summary lists: Python 3.

Does Ctf AI ML access the network?

SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Ctf AI ML safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Ctf AI ML use?

No licence was found for Ctf AI ML or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Ctf AI ML use?

About 533 tokens (SKILL.md is roughly 2.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 15k tokens, read only when the agent opens those files.

What are the alternatives to Ctf AI ML?

Skills that share tags, products or a category with Ctf AI ML: Reverse Flow (lingbol088-spec/reverse-flow-skill, 940 stars), Ctf Osint (ljagiello/ctf-skills, 3.4k stars), Penetration Flow (lingbol088-spec/ReiPenFlow, 222 stars) and Helloctf Skill (ProbiusOfficial/Hello-CTF, 4.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ctf AI ML?

wgpsec (a GitHub organization) maintains it in wgpsec/AboutSecurity, which has 1,777 GitHub stars. The repository holds 74 skills in this directory. The repository was last updated on October 8, 2026.

Source: wgpsec/AboutSecurity on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Ctf AI ML

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Files

Compare with similar skills

Similar skills

More from wgpsec/AboutSecurity

Related

Questions about Ctf AI ML