# cordon

> cordon — ilyautov-cordon. Use this tool when you need to securely interact with untrusted content and ensure deterministic agent actions. Cordon removes hidden layers, tracks data origin, and confines calls within intent boundaries, solving problems related to data security and integrity. It provides a reliable interface for inputs from untrusted sources and outputs controlled actions, ideal for use cases requiring strict data handling and agent control.

Canonical page: https://skillsregistry.net/skills/ilyautov-cordon  
JSON: https://api.skillsregistry.net/v1/skills/ilyautov-cordon

## Description

A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Gemini CLI, MCP hosts and LangChain. | Файрвол от промпт-инъекций для ИИ-агентов без ИИ внутри: агент читает что угодно и слушается только вас.

## Trust

- **Trust score (0–1):** 0.86
- **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/ilyautov/cordon)

## 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": "ilyautov-cordon"
    }
  }
}
```

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