Advertise
MCP.so
Sign In
A

Agent Skill Scanner MCP Server

@rexcoleman

Repository

Basic information

Category

AI & Agents

Transports

stdio

Author

rexcoleman

Submitted by

Rex Coleman

About Agent Skill Scanner MCP Server

Scan OpenClaw SKILL.md and MCP tool definition files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks. The only scanner targeting agent skill file formats.

#security#agent-security#prompt-injection#llm-security#skill-scanner

Agent Skill Scanner MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "agent-skill-scanner": {
      "command": "python3",
      "args": [
        "/path/to/agent-skill-scan-mcp/server.py"
      ],
      "env": {}
    }
  }
}

Agent Skill Scanner MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is Agent Skill Scanner?

Agent Skill Scanner scans OpenClaw SKILL.md and Model Context Protocol (MCP) tool definition files for security vulnerabilities directly from Claude Code. It is for developers building agent skill files who need targeted security analysis beyond generic SAST tools.

How to use Agent Skill Scanner?

Install with pip install agent-skill-scanner, then configure in Claude Code's MCP settings by adding the agent-skill-scanner server pointing to the server.py script. Use the tools scan_skill_file (to scan a single file) or scan_directory (to recursively scan a directory) from within Claude.

Key features of Agent Skill Scanner

  • 22 detection rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.
  • Targets OpenClaw SKILL.md and MCP tool definition formats (missed by generic SAST tools).
  • Returns findings with severity, rule ID, description, and evidence.
  • Recursively scans directories for agent skill files.
  • Runs fully locally via stdio; no network calls after install.
  • Source is open and auditable on GitHub.

Use cases of Agent Skill Scanner

  • Scan a single agent skill file for vulnerabilities before deployment.
  • Recursively scan a directory of skill files to get aggregated findings.
  • Integrate into a CI pipeline using the companion GitHub Action.
  • Identify hidden attacks like system prompt override or shell spawning in skill files.

Frequently asked questions

1

What does Agent Skill Scanner detect that other scanners miss?

It detects vulnerabilities in OpenClaw SKILL.md and MCP tool definitions – markdown-embedded code and YAML skill configurations that generic SAST tools (semgrep, CodeQL) completely miss.

2

What are the runtime requirements for Agent Skill Scanner?

Python 3.10 or newer and the scanner engine installed via pip. No external services or network connections are required after the initial installation.

3

Where does Agent Skill Scanner store or send data?

All scanning is done locally via stdio. There is no data collection, telemetry, or outbound network calls beyond the initial `pip install`.

4

What are the limitations of Agent Skill Scanner?

It uses pattern-based detection only (no semantic analysis). It is designed specifically for OpenClaw SKILL.md and MCP tool definitions, and its rules cover known attack patterns from published research, not zero-days.

5

What transport does Agent Skill Scanner use for MCP?

It uses stdio transport to communicate with Claude Code. No HTTP or network transport is involved.

Comments

More AI & Agents MCP servers

L

Legion MCP

faulkj

MCP-native LLM councils for debates, juries, blind panels, voting, refinement, and custom multi-model deliberation.

1

AskOne: Live Q&A and Polls

phuryn

Run free live audience Q&A and polls from your agent: start an AskOne room, add and launch a poll, approve or hide questions and mark them answered, close the room, then read the questions as a FAQ draft and get the resu

Plainpaper

Plainpaper

The AI marketing canvas for Claude and MCP agents. Your agent drafts campaigns as cards on a shared board, briefed by your brand rules, approved by you.

HeyLead: LinkedIn Outreach & Lead Generation MCP Server

D4umak

HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.

9

Brontide

Beeswaxpat

Free mech duel built for AI agents. An agent pilots a mech over MCP with no sign-in and fights the house bot, another agent or a person. Every match lands on a public leaderboard.

Advertise