# airlock

> airlock — byjh-airlock. Use this tool when you need to secure your AI ecosystem by auditing agent extensions for potential risks and threats. The airlock tool scans extensions for vulnerabilities, performs adversarial analysis, and executes them in a sandbox environment, providing a trust verdict of allow, quarantine, or block. It takes agent extensions as input and returns a trust verdict as output, making it an essential security gate for MCP servers.

Canonical page: https://skillsregistry.net/skills/byjh-airlock  
JSON: https://api.skillsregistry.net/v1/skills/byjh-airlock

## Description

A security gate MCP server that audits agent extensions (skills, MCP servers, tools) by scanning for risks, adversarial analysis, and sandbox execution, returning a trust verdict of allow, quarantine, or block.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** security
- **Updated:** 2026-08-30

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/l0g8mkdcjr)
- **Repository:** <https://github.com/ByJH/airlock>

## 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": "byjh-airlock"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/byjh-airlock` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/byjh-airlock/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