Manyoyo — Security skill for Claude Code
AI Agent CLI Security Sandbox.
How to install Manyoyo
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open xcanwin/manyoyo and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Manyoyo does
AI Agent CLI Security Sandbox. 一款AI智能体安全沙箱,保障PC安全,可以随心所欲运行YOLO/SOLO模式,例如claude --dangerously-skip-permissions
Alternatives in Security
- Security Guardian — Comprehensive security analysis for RTK CLI tool, focusing on command injection, shell escaping, hook security 11.9k ★
- Anthropic Cybersecurity Skills — 734+ structured cybersecurity skills for AI agents · MITRE ATT&CK mapped · agentskills.io open standard · Work 3.8k ★
- Trail Of Bits Claude-code-config — Opinionated production defaults from a top security firm: sandboxing, permissions, hooks, skills, MCP server c 1.6k ★
README
面向 AI Agent CLI 的 Docker / Podman 安全沙箱。
用于隔离 Claude Code、Codex、Gemini、OpenCode 等命令行智能体,降低宿主机风险,并保持可复现的运行环境。
文档:https://xcanwin.github.io/manyoyo/
生态仓库
| 仓库 | 定位 |
|---|---|
| manyoyo | CLI + 容器运行时 + Web 服务 |
| manyoyo-app | Flutter 原生 UI 客户端(macOS / Windows / iOS / Android) |
| manyoyo-studio | Electron 桌面端 + Capacitor 移动端 |
为什么是 MANYOYO
AI Agent CLI 往往需要:
- 访问代码仓库
- 执行 shell 命令
- 读写文件
- 安装依赖或调用容器能力
直接在宿主机上裸跑这些工具,风险边界通常不清晰。**MANYOYO** 的目标不是替代容器平台,而是把常见 Agent CLI 的运行方式收敛到一个更清晰、可复现、可审计的沙箱入口。
你可以把它理解为:
- 面向 Agent CLI 的运行包装层
- 面向团队协作的配置与镜像约定
- 面向高风险模式的显式边界说明
核心能力
- 多 Agent 支持:支持
claude、gemini、codex、opencode - 容器隔离:基于 Docker / Podman 运行,降低宿主机暴露面
- YOLO / SOLO 工作流:适配跳过权限确认的高效率模式
- 统一配置入口:集中管理
runs.、环境变量、挂载与镜像参数 - 命令可预览:支持查看配置合并结果与最终命令拼装
- 会话与 Web 模式:支持容器会话管理与网页访问入口
- 镜像可定制:支持 common / full / 自定义工具集镜像
Related Skills
Claude Code Ship Gate
Pre-push quality gate for Claude Code that runs above git, so git push --no-verify can't skip it. Tests, code
Agentic AI Security Starter Kit
Working code examples to defend against Agentic AI threats: prompt injection detection, Claude Code hooks, OPA
Claude Bash Tutor Skill
Claude Skill teaching bash from the ground up: 17 units, prompt basics through security and debugging. Every e
Bulbi
Security-first sandbox for autonomous AI coding agents. Run Claude Code, Codex and other AI CLIs in full-auto
Pentest
Run an AI-powered penetration test against a target URL + source code repo. Usage: /pentest [--config ] --ski
AI Ready Audit SEO GEO AEO Skill For Claude
A Claude Skill that audits any website for SEO, GEO (Generative Engine Optimization), and AEO (Answer Engine O
Related Agents
Tsk - AI Agent Task Manager And Sandbox
by dtormoen - A Rust CLI tool that lets you delegate development tasks to AI agents running in sandboxed Docke
Codex Runner
codex CLI(codex exec / codex exec resume)を最後まで走り切らせる専任エージェント。呼び出し元(メイン Claude / スキル)からプロンプト・model・effort・sandb
Omhc Tester
Hands-on tester for omhc. Use after a change is implemented (and ideally reviewed) to exercise it for real in