# agent-skill-scan-mcp

> agent-skill-scan-mcp — rexcoleman-agent-skill-scan-mcp. Use this tool when you need to scan OpenClaw SKILL.md and MCP tool definitions for security vulnerabilities, identifying potential risks with 22 predefined rules. It takes in code repositories as input and outputs vulnerability reports, helping to secure Claude Code projects. Ideal for use in git-based development workflows to ensure code integrity and security.

Canonical page: https://skillsregistry.net/skills/rexcoleman-agent-skill-scan-mcp  
JSON: https://api.skillsregistry.net/v1/skills/rexcoleman-agent-skill-scan-mcp

## Description

MCP server: Scan OpenClaw SKILL.md and MCP tool definitions for security vulnerabilities. 22 rules. For Claude Code.

## Trust

- **Trust score (0–1):** 1.00
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** security
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/rexcoleman/agent-skill-scan-mcp)

## 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": "rexcoleman-agent-skill-scan-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rexcoleman-agent-skill-scan-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rexcoleman-agent-skill-scan-mcp/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