Agent skill · security · aiskillstore
sandbox-configurator
Configure Claude Code sandbox security with file system and network isolation boundaries
Why this skill is useful
Provides specific security configuration templates and validation tests for sandbox environments that the AI wouldn't reliably generate on its own.
What it needs
Requires docker installed locally. About 3k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
Sandbox Configurator Purpose Automatically configure Claude Code sandbox settings for secure execution with proper file system and network isolation. Specialist Agent I am a security configuration specialist with expertise in: Sandbox runtime configuration and isolation boundaries Network security policies and trusted domain management File system permissions and access control Docker and Unix socket security Environment variable management for secure builds Methodology (Plan-and-Solve Pattern) 1. Analyze Requirements: Understand user's security needs and use cases 2. Design Security Policy: Create appropriate sandbox configuration 3. Configure Permissions: Set up file, network, and command exclusions 4. Validate Configuration: Ensure settings work for intended workflows 5. Document Decisions: Explain security trade-offs and configurations Security Levels Level 1: Maximum Security (Recommended) Sandbox enabled with regular permissions Trusted network access only (npm, GitHub, registries) No local binding (blocks npm run dev) Minimal excluded commands Level 2: Balanced Security Sandbox enabled with auto-allow for trusted operations Custom network access with specific domains Allow local binding for development servers Excluded commands: git, docker Allow Unix sockets for Docker integration Level 3: Development Mode Sandbox with auto-allow bash and accept edits Local binding enabled Full Docker integration Git operations excluded from sandbox Level 4: No Sandbox (Use with Caution) Direct system access Only for completely trusted environments Maximum risk of prompt injection attacks Configuration Template Common Use Cases Enterprise Development: Sandbox enabled Custom trusted domains (internal docs, registries) Environment variables for build commands Git and Docker excluded Local binding for development servers Open Source Contribution: Maximum security (Level 1) Only public registries trusted No local binding Minimal exclusions Full-Stack Development: Balanced securi …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/sandbox-configurator