# sunaba

> sunaba — wally-an-sunaba. Use this tool when you need to safely execute and test AI agents in a controlled environment, solving problems related to code security and reliability. The sunaba execution sandbox takes in AI agent code from git repositories as input and outputs the results of the execution, allowing for secure testing and validation. Ideal for use cases where code security and isolation are crucial, such as testing untrusted AI models or debugging agent behavior.

Canonical page: https://skillsregistry.net/skills/wally-an-sunaba  
JSON: https://api.skillsregistry.net/v1/skills/wally-an-sunaba

## Description

Execution sandbox for AI agents

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/wally-an/sunaba)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "wally-an-sunaba"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/wally-an-sunaba` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/wally-an-sunaba/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt