sandbox

Solid

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.

AI & Automation 667 stars 122 forks Updated today Apache-2.0

Install

View on GitHub

Quality Score: 88/100

Stars 20%
94
Recency 20%
100
Frontmatter 20%
40
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Sandbox Environment Execute code, commands, and complex tasks securely in isolated Docker containers running **AlmaLinux 9.4**. ## Core Capabilities The sandbox environment provides fully isolated execution spaces with: 1. **Command Execution** - Run shell commands, scripts, and programs 2. **File Operations** - Read/write files, browse directories, manage filesystems 3. **Code Execution** - Safely execute and test code 4. **Claude AI Tasks** - Available for advanced use cases when explicitly requested by users 5. **Attachment Upload/Download** - Upload generated files to Wegent for user download, or download user attachments for processing ## When to Use Use this skill when you need to: - ✅ Execute shell commands or scripts - ✅ Run and test code - ✅ Read, write, or manage files - ✅ Perform multi-step programming tasks - ✅ Git operations (clone, commit, push, etc.) - ✅ Require isolated environment for safety **Note**: The `sub_claude_agent` tool should only be used when the user explicitly requests Claude AI assistance (e.g., "use Claude to generate...", "ask Claude to create..."). ## Available Tools ### Command Execution #### `exec` Execute shell commands in the sandbox environment. **Use Cases:** - Run single commands or scripts - Directory operations (create, delete, move) - Install dependencies, run tests - View system information **Parameters:** - `command` (required): Shell command to execute - `working_dir` (optional): Working directory path - `timeout` ...

Details

Author
wecode-ai
Repository
wecode-ai/Wegent
Created
6 months ago
Last Updated
today
Language
Python
License
Apache-2.0

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

DevOps & Infrastructure Listed

dev-sandbox

Use when work should run inside a per-branch Docker dev sandbox - initiating one, checking state, attaching over ssh, executing commands or tests inside the Linux clone, refreshing it from origin, and tearing it down. Trigger on "run this in a sandbox", "spin up a sandbox", "sandbox status", "attach to the sandbox", "test this on Linux", "verify cross-platform", "run the suite in the container", working a second feature branch in parallel, or ANY time an in-sandbox result is about to be trusted - the origin-clone caveat here decides whether that result means anything.

2 Updated yesterday
petermcalister
AI & Automation Solid

sandbox-routing

SELF-CORRECT tool choice. About to Read a long file just to extract one piece of info? Use a sandbox tool that returns only the summary. About to run a long shell command? Same. Sandbox keeps raw output OUT of context — only summaries land. Triggers when about to flood context with large output.

11 Updated today
wrg32786
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 5 days ago
Hoja-Solutions