kesekit-guide-ko

kesekit-guide-ko is a skill for Claude Code from cdppcorp/KESE-KIT. It costs 121 tokens per session (2,369 once invoked), scanned A, original, MIT.

A generator for secure-coding prompts and guides for AI tools such as Claude, ChatGPT, Cursor, and Copilot. It covers web security, AI security, robot security, space systems, language-specific coding, and zero-trust architecture.

In plain words
What is it for?
Use it to create copy-and-paste prompts based on KISA guidance, OWASP, and CWE vulnerability patterns. It supports web, server, database, AI, robot, satellite, and zero-trust projects.
Why use it?
It gives developers security guidance suited to the type of system and programming language they are working with. This makes common risks such as SQL injection, cross-site scripting, prompt injection, and data poisoning easier to address.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the kesekit plugin — 8 skills shipped together

Good fit Use it to create copy-and-paste prompts based on KISA guidance, OWASP, and CWE vulnerability patterns. It supports web, server, database, AI, robot, satellite, and zero-trust projects.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cdppcorp/kese-kit/kesekit-guide-ko
Install

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.

Any agent
npx skills add cdppcorp/KESE-KIT --skill kesekit-guide-ko
Clone the repo
git clone --depth 1 https://github.com/cdppcorp/KESE-KIT

Made for: Claude Code.

Or install kesekit, the plugin that ships this one along with the rest of its 8 skills.

Wrote 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.

agentmods badge for kesekit-guide-ko

README.md
[![agentmods](https://agentmods.dev/badge/skills/cdppcorp/kese-kit/kesekit-guide-ko.svg)](https://agentmods.dev/skills/cdppcorp/kese-kit/kesekit-guide-ko)
Your own site
<a href="https://agentmods.dev/skills/cdppcorp/kese-kit/kesekit-guide-ko"><img src="https://agentmods.dev/badge/skills/cdppcorp/kese-kit/kesekit-guide-ko.svg" alt="Measured on agentmods" height="20"></a>
Per session 121 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,369 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00121 $0.02369
Opus 5 $0.00060 $0.01184
Sonnet 5 $0.00024 $0.00474
Haiku 4.5 $0.00012 $0.00237

Measured 8d ago against content hash 0aaf52674384, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

kesekit-guide-ko 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 8d 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.

skills-ko/kesekit-guide-ko/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KESE 시큐어 코딩 프롬프트 생성기

KISA 가이드라인과 국제 표준(OWASP, CWE)을 기반으로 AI 도구용 시큐어 코딩 프롬프트를 생성합니다.

가이드라인 선택

# 가이드라인 설명
1 CII 시큐어코딩 전통적 보안 취약점 (SQL Injection, XSS 등)
2 AI 보안 시큐어코딩 AI 특화 보안 (Prompt Injection, 데이터 중독 등)
3 로봇 보안 시큐어코딩 로봇 특화 보안 (IEC 62443, 펌웨어, 통신 프로토콜)
4 우주 보안 시큐어코딩 우주 특화 보안 (CCSDS, 위성 프로토콜, GSaaS, 공급망)
5 시큐어코딩 (언어별) 언어별 시큐어코딩 (JS, Python, pseudo code)
6 제로트러스트 가이드 제로트러스트 아키텍처 및 성숙도 평가 가이드 (8개 핵심요소, ~396항목)

웹/서버/DB 개발 → CII / AI 모델/LLM/AI 서비스 개발 → AI 보안 / 로봇 펌웨어, ROS/ROS2, 로봇 API, 산업 프로토콜 개발 → 로봇 보안 / 위성 통신, 지상국, GSaaS API, 우주 공급망 → 우주 보안 / JavaScript, Python, 기타 언어 → 시큐어코딩 (언어별) Zero Trust, ZTA, ZTNA, 제로트러스트, 마이크로세그멘테이션, microsegmentation, SDP, SASE, PEP/PDP, never trust always verify → 제로트러스트


CII 분기 시

templates/cii/webapp.md를 참조하여 CWE 기반 시큐어 코딩 프롬프트를 생성합니다. 점검/수정 스크립트는 scripts/cii/에 있습니다.

실행 흐름

  1. 사용자에게 대상 컨텍스트 확인 (언어, 프레임워크, 기능 유형)
  2. 커스터마이징된 시큐어 코딩 프롬프트 생성
  3. 관련 CWE 패턴 및 KISA 가이드라인 포함
  4. 복사-붙여넣기 형식으로 프롬프트 제공

주요 CWE 패턴

CWE 이름 방지 방법
CWE-20 부적절한 입력 검증 모든 입력 검증
CWE-22 경로 조작 경로 정규화 및 검증
CWE-78 OS Command Injection shell 피하기, 인자 리스트
CWE-79 XSS 출력 인코딩, CSP
CWE-89 SQL Injection 매개변수화된 쿼리
CWE-94 Code Injection eval(), exec() 피하기
CWE-287 부적절한 인증 검증된 프레임워크 사용
CWE-327 약한 암호화 AES-256, RSA-2048+
CWE-352 CSRF CSRF 토큰
CWE-434 무제한 업로드 타입, 크기, 이름 검증
CWE-502 안전하지 않은 역직렬화 JSON 사용
CWE-611 XXE 외부 엔티티 비활성화
CWE-798 하드코딩된 자격 증명 환경 변수 사용
CWE-918 SSRF URL 검증, 사설 IP 차단

언어별 프롬프트 생성

사용자가 지정한 언어에 맞게 시큐어 코딩 프롬프트를 생성합니다:

  • Python: SQL Injection, Command Injection, 경로 조작, 역직렬화, 패스워드 해싱
  • JavaScript/Node.js: XSS, SQL Injection, Command Injection, 안전한 난수
  • Java: SQL Injection, XXE, 경로 조작, 역직렬화
  • Go, Rust, C# 등 요청 시 해당 언어에 맞게 생성

기능별 프롬프트 생성

  • 인증 구현, 파일 업로드, API 보안, 세션 관리 등

Read the full file on GitHub · 145 lines

Files

What ships with it

60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 8d ago First seen · 145 lines · 121 tokens per session scan A 0aaf52674384

Subscribe to this mod's changes

kesekit-guide-ko is a skill published in the GitHub repository cdppcorp/KESE-KIT (356 stars, last pushed 5mo ago), licensed MIT. It adds 121 tokens to every session and 2,369 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens