poco-agent — security grade SAFE, quality 66/100

Security audit verdict: SAFE · quality 66/100

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 poco-ai · Claude Skill · ★ 1.1k

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

🔒 Is poco-agent safe to install? View the security audit →

About poco-agent

Poco: Your Pocket Coworker A safer, more beautiful, and easier-to-use OpenClaw alternative English | 简体中文 Core Features Server and Channel Collaboration Work in long-lived servers with channels, DMs, and reply threads. Mention persistent agents in the conversation, turn messages into trackable tasks, inspect execution progress in the drawer, and publish outputs into shared files for people and other agents to reuse. Secure Sandbox All tasks run in an isolated container. Feel free to install dependencies, modify files, and execute commands — without affecting the host environment. Local Directory Mounting — mount host directories into the sandbox so the agent can work with your real project files direct

agentaichatbotclaude-codeclawdbotmanusopenclaw

Quick Facts

Stars1,122
Forks104
LanguageTypeScript
CategoryClaude Skill
LicenseMIT
Quality Score65.5972641591565/100
Open Issues1
Last Updated2026-03-09
Created2026-01-08
Platformsbrowser, claude-code, node
Est. Tokens~1007k

poco-agent alternative? Top 6 similar tools

Looking for a poco-agent alternative? If you're comparing poco-agent 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.

  • tokscale by junhoyeo · ⭐ 5.5k

    🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of toke

  • openakita by openakita · ⭐ 2.0k

    An open-source AI assistant framework with skills and agent architecture

  • Wegent by wecode-ai · ⭐ 859

    Plan, build, and deliver with an open-source, self-hostable AI workspace for coding, collaboration, and automa

  • argo by xark-argo · ⭐ 827

    ARGO is an open-source AI Agent platform that brings Local Manus to your desktop. With one-click model downloa

  • casibase by casibase · ⭐ 4.5k

    ⚡️AI Cloud OS: Open-source enterprise-level AI knowledge base and MCP (model-context-protocol)/A2A (agent-to-a

  • antigravity-claude-proxy by badrisnarayanan · ⭐ 3.9k

    Proxy that exposes Antigravity provided claude / gemini models, so we can use them in Claude Code and OpenClaw

More Claude Skill Tools

Explore other popular claude skill tools:

View all Claude Skill tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is poco-agent?

poco-agent is A more beautiful and easier-to-use alternative to OpenClaw. It features a nicer Web UI, built-in IM support, and a sandboxed runtime for improved safety. Under the hood, it is powered by a Claude Code. It is categorized as a Claude Skill with 1.1k GitHub stars.

What programming language is poco-agent written in?

poco-agent is primarily written in TypeScript. It covers topics such as agent, ai, chatbot.

How do I install or use poco-agent?

You can find installation instructions and usage details in the poco-agent GitHub repository at github.com/poco-ai/poco-agent. The project has 1.1k stars and 104 forks, indicating an active community.

What license does poco-agent use?

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

What are the best alternatives to poco-agent?

The top alternatives to poco-agent on Agent Skills Hub include tokscale, openakita, Wegent. 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