claw-hwp — security grade SAFE, quality 60/100

Security audit verdict: SAFE · quality 60/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by DoHyun468 · Claude Skill · ★ 162

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is claw-hwp safe to install? View the security audit →

About claw-hwp

claw-hwp Claude 에서 한글 문서 (.hwp / .hwpx) 를 다루는 Agent Skill — 읽기 · 만들기 · 편집 + 한컴오피스/한컴독스 호환 저장 보장. Claude Code · Desktop · 웹 어디서든. rhwp 파싱 엔진 + 자체 편집 인프라. 한국어 · English 소개 는 Claude 가 한글 문서 (.hwp / .hwpx) 를 직접 다룰 수 있도록 해주는 Agent Skill 입니다. 한국 사무 환경에서는 한컴오피스 형식이 사실상 표준인데, Claude 는 기본적으로 이 형식을 읽거나 편집하지 못합니다. 이 스킬을 설치하면 Claude 가 다음 작업을 할 수 있습니다: 읽기 — .hwp / .hwpx 의 본문, 표, 메타데이터 추출 만들기 — 새 문서 작성 (제목·문단·표·이미지·페이지 나누기 + 글자 서식(굵게·기울임·밑줄·취소선·형광펜·글자색·크기·폰트)와 문단 서식(정렬·줄간격·들여쓰기·여백·배경색) 포함). 와 어느 형식이든 표가 포함된 새 문서를 만들 수 있습니다. 편집 — 기존 문서를 원본 형식 그대로 편집 ( ↔ 변환 없이). 는 byte-level raw-patch 로 (셀 내용·텍스트 치환·문단/표 추가·페이지 설정·글자/문단 서식), 는 XML 직접 편집으로 (셀·머리·꼬리말·글머리/번호 목록·각주·하이퍼링크·표 신규 삽입 등). 양쪽 다 표를 보존합니다. 변환 — .hwp ↔ .hwpx

agent-skillanthropicclaudeclaude-codeclaude-coworkclaude-pluginclaude-skillcodexdocument-automationhancom

Quick Facts

Stars162
Forks26
LanguageJavaScript
CategoryClaude Skill
LicenseMIT
Quality Score60.3489653153657/100
Open Issues1
Last Updated2026-09-20
Created2026-05-07
Platformsclaude-code, codex, node
Est. Tokens~15k

claw-hwp alternative? Top 6 similar tools

Looking for a claw-hwp alternative? If you're comparing claw-hwp with other claude skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • hwp-mcp by treesoop · ⭐ 68

    MCP server for reading and writing HWP/HWPX (Korean Hangul) documents — built on rhwp. 34 tools, Claude/Cursor

  • moai-cowork by modu-ai · ⭐ 302

    비개발자를 위한 한국 실무 AI 코워커 패밀리 — Claude Cowork·ChatGPT Work에서 /project 한 번으로 시작

  • compose-skill by aldefy · ⭐ 561

    Jetpack Compose Agent Skill — AI-powered coding guidance with actual androidx/androidx source code receipts. W

  • patina by devswha · ⭐ 358

    AI-writing humanizer for KO/EN/ZH/JA

  • cowork-plugins by modu-ai · ⭐ 267

    모두의 AI (MoAI) — Claude Cowork & Claude Code 한국 실무 도메인 AI 하네스·플러그인 마켓플레이스. 사업계획서·세무·법률·HR·마케팅·커머스·BI·콘텐츠 도메인 스킬

  • skill-conductor by smixs · ⭐ 160

    Architecture-first skill lifecycle for AI agents. BinEval binary scoring with threshold-blind, cross-family-ca

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is claw-hwp?

claw-hwp is AI(Claude·클로드 · Codex·코덱스)로 한글 문서(.hwp/.hwpx)를 한컴 없이 읽고·만들고·편집하는 오픈소스 스킬 · Read, create & edit Korean HWP in Claude/Codex. It is categorized as a Claude Skill with 162 GitHub stars.

What programming language is claw-hwp written in?

claw-hwp is primarily written in JavaScript. It covers topics such as agent-skill, anthropic, claude.

How do I install or use claw-hwp?

You can find installation instructions and usage details in the claw-hwp GitHub repository at github.com/DoHyun468/claw-hwp. The project has 162 stars and 26 forks, indicating an active community.

What license does claw-hwp use?

claw-hwp is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to claw-hwp?

The top alternatives to claw-hwp on Agent Skills Hub include hwp-mcp, moai-cowork, compose-skill. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Claude Skill tools