# arc-skill-sandbox

> arc-skill-sandbox — trypto1019-arc-skill-sandbox. Use this tool when you need to test and validate untrusted skills in a secure and isolated environment before installing them, solving problems related to skill security and compatibility. It provides an interface to input skills for testing and outputs results on their functionality and potential risks. Ideal for use cases where skill installation poses a risk to the main system, such as testing third-party or unverified skills.

Canonical page: https://skillsregistry.net/skills/trypto1019-arc-skill-sandbox  
JSON: https://api.skillsregistry.net/v1/skills/trypto1019-arc-skill-sandbox

## Description

Test untrusted skills in an isolated environment before installing.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-05-20

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** other
- **Updated:** 2026-09-16

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/trypto1019-arc-skill-sandbox)

## 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": "trypto1019-arc-skill-sandbox"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/trypto1019-arc-skill-sandbox` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/trypto1019-arc-skill-sandbox/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