zcode-keysmith — security grade SAFE, quality 65/100

Security audit verdict: SAFE · quality 65/100

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 Jia-Ethan · Agent Tool · ★ 279

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

🔒 Is zcode-keysmith safe to install? View the security audit →

About zcode-keysmith

zcode-keysmith ZCode App managed true system-role entrypoint. 简体中文 · English · Reference · 智能体安装 / Agent install · License 简体中文 这是什么 为本机 ZCode 桌面端安装一条受管理的 入口。它把仓库里的 安装成用户目录里的受管理版本,让 ZCode 新启动的 agent-server 进程读取这份文件,进入 ZCode runtime 的 system message 注入路径。ZCode App 原包保持完整:安装器只写用户目录和用户 LaunchAgent;API key、provider、MCP、settings 和项目文件继续由 ZCode 自身管理,安装器不读取、不保存、不打印这些内容。 默认写入位置: 原理 ZCode 桌面端启动 agent-server 时会读取两个环境变量: 把 指向 。wrapper 做三件事: 读取 ZCode 自带 runtime:/Applications/ZCod

agent-toolslinux-domacospythonsystem-rolezcodezcode-app

Quick Facts

Stars279
Forks59
LanguagePython
CategoryAgent Tool
LicenseMIT
Quality Score65.1199781123064/100
Open Issues2
Last Updated2026-09-22
Created2026-07-04
Platformspython
Est. Tokens~14k

Compatible Skills

These tools work well together with zcode-keysmith for enhanced workflows:

  • CCteam-creator — semantic(0.18)+complementary+same_lang+similar_pop+shared_platform (56%)

zcode-keysmith alternative? Top 6 similar tools

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

  • open-extract by velocitybolt · ⭐ 189

    Structured Data Extractor for AI Agents. Search your documents or the web for specific data and get it back in

  • os-ai-computer-use by 777genius · ⭐ 176

    AI controls your OS. OS AI Computer Use, OS and API agnostic. For now on OpenAI and Anthropic API. Desktop app

  • ai-agent-tools-catalog by GetStream · ⭐ 164

    Explore the must-have external ready-made toolkits to integrate with your AI agents built with Python and Type

  • cheatengine-mcp-bridge by miscusi-peek · ⭐ 1.2k

    Connect Cursor, Copilot & Claude AI directly to Cheat Engine via MCP. Automate reverse engineering, pointer sc

  • MassGen by massgen · ⭐ 1.1k

    🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating

  • arcade-mcp by ArcadeAI · ⭐ 1.0k

    MCP Server Framework and Tool Development library for building custom capabilities into agents.

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Python Agent Tools

Frequently Asked Questions

What is zcode-keysmith?

zcode-keysmith is ZCode App managed true system-role entrypoint. It is categorized as a Agent Tool with 279 GitHub stars.

What programming language is zcode-keysmith written in?

zcode-keysmith is primarily written in Python. It covers topics such as agent-tools, linux-do, macos.

How do I install or use zcode-keysmith?

You can find installation instructions and usage details in the zcode-keysmith GitHub repository at github.com/Jia-Ethan/zcode-keysmith. The project has 279 stars and 59 forks, indicating an active community.

What license does zcode-keysmith use?

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

What are the best alternatives to zcode-keysmith?

The top alternatives to zcode-keysmith on Agent Skills Hub include open-extract, os-ai-computer-use, ai-agent-tools-catalog. 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 Agent Tool tools