# SkillAudit

SkillAudit scans agent skills and MCP servers for security threats before you install or execute them in a project.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · 4310 installs
- Author: megamind-0x
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://smithery.ai/server/megamind-0x/skillaudit
- Updated: 2026-02-15
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/skillaudit

## What it does

The server connects to coding agents over HTTP to audit external extensions. It detects credential harvesting, unauthorized exfiltration, hidden malicious routines, and prompt injections across 80+ threat patterns.

Four core tools handle the inspection: `scan_url` evaluates a remote address, `scan_github` analyzes repository files, `gate_check` decides whether to allow or block an install, and `reputation_check` queries domain history. While standard requests run on the free tier, deep scans depend on x402 micropayments.

## Requirements
- Remote server: `https://skillaudit--megamind-0x.run.tools`

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http skillaudit https://skillaudit--megamind-0x.run.tools
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add skillaudit --url https://skillaudit--megamind-0x.run.tools
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "skillaudit": {
            "url": "https://skillaudit--megamind-0x.run.tools"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "skillaudit": {
            "type": "http",
            "url": "https://skillaudit--megamind-0x.run.tools"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http skillaudit https://skillaudit--megamind-0x.run.tools
```

## When to use it
- scan GitHub repositories for malicious skill code and risks
- verify third-party skill endpoints before adding them to your setup
- check domain reputation against past scan records
- detect prompt injections and credential theft patterns

## Example prompts
- Check this repository for security risks using `scan_github`.
- Run a `gate_check` on the skill URL before I approve the installation.
- Look up domain reputation with `reputation_check`.

## Similar
- [inter-agent-comm-security-detection](https://affpapa.org/en/nevibecode/skills/inter-agent-comm-security-detection.md) — skill · ★ 7607 repo stars
- [autopilot](https://affpapa.org/en/nevibecode/commands/autopilot.md) — command · ★ 16193 repo stars
- [darkmoon](https://affpapa.org/en/nevibecode/plugins/darkmoon.md) — plugin · ★ 1596 repo stars
- [Security Auditor](https://affpapa.org/en/nevibecode/mcp/security-auditor.md) — MCP server · 148 installs
- [hack](https://affpapa.org/en/nevibecode/skills/hack.md) — skill · 4800 installs
- [security-testing](https://affpapa.org/en/nevibecode/skills/aj-geddes-security-testing.md) — skill · 610 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
