sandbox

Solid

Execute commands in isolated sandboxes for security. Use when running untrusted code, system commands, or operations that could affect the host system. Automatically detects the right runtime (Python, Node, Rust, Go, Ruby, etc.) from the command.

AI & Automation 59 stars 6 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
59
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Sandbox Skill Execute commands in secure, isolated containers using agentkernel. This provides hardware-level isolation to protect the host system from potentially dangerous operations. ## When to Use This Skill Use this skill when: - Running untrusted or generated code - Executing shell commands that could modify system state - Testing code in a clean environment - Running build/test commands that might have side effects - Executing code from external sources - Any operation where isolation is beneficial for security Do NOT use this skill for: - Simple file reads/writes (use standard tools) - Git operations (use standard tools) - Operations that need access to host credentials or SSH keys ## Instructions ### Basic Usage Run any command in an isolated sandbox: ```bash agentkernel run <command> [args...] ``` For compound commands with `&&` or `||`, wrap in `sh -c`: ```bash agentkernel run sh -c 'npm install && npm test' ``` The runtime is auto-detected from the command: ```bash # Python agentkernel run python3 script.py agentkernel run pip install package-name agentkernel run pytest # Node.js agentkernel run node script.js agentkernel run npm test agentkernel run npx create-react-app my-app # Rust agentkernel run cargo build agentkernel run cargo test # Go agentkernel run go build agentkernel run go test ./... # Ruby agentkernel run ruby script.rb agentkernel run bundle exec rspec # And more: PHP, Java, C/C++, Elixir, Lua, Terraform... ``` ### Specifying ...

Details

Author
thrashr888
Repository
thrashr888/agentkernel
Created
7 months ago
Last Updated
today
Language
Rust
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Featured

sandbox

Provides read_file/write_file/exec/list_files/read_file/write_file for running process and managing filesystems in the sandbox. Ideal for code testing, file management, and command execution. The sub_claude_agent tool is available for advanced use cases. You MUST load this skill BEFORE use sandbox tools.

848 Updated today
wecode-ai
AI & Automation Featured

ai-coding-agents-execution-sandbox

Designs execution sandboxes for coding agents. Use when modeling process isolation, filesystem policy, network controls, workspace mounts, or destructive-command boundaries.

87 Updated 1 weeks ago
vasilyu1983
AI & Automation Listed

sandboxing-agentic-systems

Contain an agent that runs code or reads untrusted content, layer by layer. Covers OS-level filesystem and network isolation that also catches spawned subprocesses, an egress proxy that checks request provenance, treating tool outputs and fetched pages as prompt-injection vectors, and keeping credentials outside the sandbox behind a proxy. Use this whenever someone designs a sandbox for a coding or computer-use agent, asks how to safely let an agent run shell commands or browse, worries about prompt injection from tool results, needs to limit what an autonomous agent can reach or delete, or asks where an agent's credentials should live. Trigger on "sandbox the agent," "agent runs untrusted code," "prompt injection," "restrict network access," and similar. This is environment containment; deciding which actions need approval before they run is a separate concern (action gating).

1 Updated 1 months ago
Hoja-Solutions