# Sandbox Exec

> Execute commands and manage files in a Foundry sandbox.

- **Type:** Skill
- **Install:** `agentstack add skill-ic-star-tech-ccfoundry-agent-kit-sandbox-exec`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ic-star-tech](https://agentstack.voostack.com/s/ic-star-tech)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ic-star-tech](https://github.com/ic-star-tech)
- **Source:** https://github.com/ic-star-tech/ccfoundry-agent-kit/tree/main/packages/python-sdk/skills/sandbox_exec

## Install

```sh
agentstack add skill-ic-star-tech-ccfoundry-agent-kit-sandbox-exec
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Sandbox Executor Skill

## Trigger
Use this skill when the task requires executing commands in an isolated
sandbox environment, or when managing workspace files.

## Capabilities
- Acquire and release sandbox leases from the Foundry sandbox pool
- Execute shell commands inside the sandbox container
- Write files to the sandbox workspace via API
- Monitor command output and detect success/failure

## API Reference

### Acquire a sandbox lease
```http
POST {SANDBOX_DAEMON_URL}/acquire
Content-Type: application/json
x-sandbox-token: {token}

{"username": ""}
```
Returns: `{"lease_id": "...", "slot": 1, ...}`

### Execute a command
```http
POST {SANDBOX_DAEMON_URL}/leases/{lease_id}/terminal/exec
Content-Type: application/json

{"command": ""}
```
Returns: Terminal output

### Write a file to workspace
```http
PUT {SANDBOX_DAEMON_URL}/users/{username}/workspace/write
Content-Type: application/json
x-sandbox-token: {token}

{"path": "relative/path/to/file.txt", "content": "file content here"}
```

### List workspace files
```http
GET {SANDBOX_DAEMON_URL}/users/{username}/workspace/tree
x-sandbox-token: {token}
```

### Release the sandbox
```http
POST {SANDBOX_DAEMON_URL}/release
Content-Type: application/json

{"lease_id": ""}
```

## Best Practices
- Always release the sandbox lease after use (even on error — use try/finally)
- Wait 3-5 seconds after sandbox acquisition for container initialization
- Use unique markers in commands to detect success: `echo EXIT_CODE=$?`
- Set reasonable timeouts for long-running commands: `timeout 30 `
- Check pool status before acquiring: `GET /pool-status`

## Environment Variables
- `SANDBOX_DAEMON_URL`: Daemon endpoint (default: `http://localhost:9000`)
- `SANDBOX_TOKEN`: Authentication token for the daemon API

## Error Handling
- If lease acquisition fails, the pool may be full — retry after delay
- If command execution times out, the sandbox may need to be released and re-acquired
- Always check HTTP status codes: 200/201 = success, 4xx = client error, 5xx = server error

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ic-star-tech](https://github.com/ic-star-tech)
- **Source:** [ic-star-tech/ccfoundry-agent-kit](https://github.com/ic-star-tech/ccfoundry-agent-kit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ic-star-tech-ccfoundry-agent-kit-sandbox-exec
- Seller: https://agentstack.voostack.com/s/ic-star-tech
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.
