# io.github.crunchtools/airlock

> Use this tool when you need to securely extract web content from quarantined URLs or files, and require a safe fetching mechanism with robust defense against prompt injection attacks. It provides sanitized markdown output, enabling the safe reading of potentially malicious content. Ideal for use cases where security and data integrity are paramount, such as in threat intelligence or malware analysis applications.

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

## Description

Secure MCP server for quarantined web content extraction with two-layer prompt injection defense, enabling safe fetching of URLs and reading of files via sanitized markdown output.

## Trust

- **Trust score (0–1):** 0.04
- **Verification tier:** scanned
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/se9vdxvu5j)
- **Repository:** <https://github.com/crunchtools/mcp-trentina>

## 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": "crunchtools-mcp-airlock"
    }
  }
}
```

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