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 we-used-to-be · Agent Tool · ★ 121
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is Guanmo-open safe to install? View the security audit →
观墨 · GuanMo 让 Markdown 文档更易阅读、更易理解、更易创作 A Markdown workspace for better reading, understanding, and writing 📥 下载 · Download 🪟 Windows ⬇ 下载安装包 提供 NSIS (.exe) 和 WiX (.msi) 安装程序 微软商店版本更新频率会慢一些
| Stars | 121 |
| Forks | 12 |
| Language | TypeScript |
| Category | Agent Tool |
| License | MIT |
| Quality Score | 49.6166343082338/100 |
| Open Issues | 3 |
| Last Updated | 2026-08-09 |
| Created | 2026-06-03 |
| Platforms | node |
| Est. Tokens | ~13k |
These tools work well together with Guanmo-open for enhanced workflows:
Looking for a Guanmo-open alternative? If you're comparing Guanmo-open with other agent tool tools, these 2 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Lightweight registry to discover, install, and manage all public Claude plugins and agent skills for your favo
A Claude Code skill that turns PDFs, docs, and codebases into Obsidian study vaults
Explore other popular agent tool tools:
Guanmo-open is 观墨 · AI 原生 Markdown 阅读与编辑器，融合沉浸式阅读体验、AI 辅助阅读/写作、本地 RAG 知识库、长期记忆与 Agent 工具。 GuanMo · AI-native Markdown reader and editor integrating immersive reading, AI-assisted understanding, local RAG knowledge . It is categorized as a Agent Tool with 121 GitHub stars.
Guanmo-open is primarily written in TypeScript.
You can find installation instructions and usage details in the Guanmo-open GitHub repository at github.com/we-used-to-be/Guanmo-open. The project has 121 stars and 12 forks, indicating an active community.
Guanmo-open is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to Guanmo-open on Agent Skills Hub include claude-plugins, tutor-skills. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
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: