# agent-shield

> agent-shield — bazx-bit-agent-shield. Use this tool when you need to protect your AI development environment from potential security threats. Agent-Shield blocks malicious commands and API key leaks in real-time, sitting between your AI IDE and computer to monitor Model Context Protocol (MCP) tool requests. It provides a secure interface for git and other development tools, ensuring safe and reliable AI development.

Canonical page: https://skillsregistry.net/skills/bazx-bit-agent-shield  
JSON: https://api.skillsregistry.net/v1/skills/bazx-bit-agent-shield

## Description

agent-Shield sits silently between your AI IDE (Cursor, Claude Desktop) and your computer. It continuously watches the Model Context Protocol (MCP) tool requests, blocking dangerous commands and API key leaks in real-time.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** scanned
- **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/bazx-bit/agent-shield)

## 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": "bazx-bit-agent-shield"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/bazx-bit-agent-shield` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/bazx-bit-agent-shield/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