eltociear/skill-audit-mcp

Static security scanner for MCP server code, AI agent skills, and plugins. 61 attack patterns, 68+ real CVEs found.

Public

0 runs

GitHub

Run eltociear/skill-audit-mcp with an API

Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.

Input schema

The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.

Field	Type	Default value	Description
content	string		MCP server / agent skill source code to scan. Leave empty if using `url` instead.
url	string		URL to fetch and scan. Used only if `content` is empty.
max_bytes	integer	200000 Min: 1024 Max: 2000000	Maximum bytes to read from `url` (truncated, default 200000).

{
  "type": "object",
  "title": "Input",
  "properties": {
    "url": {
      "type": "string",
      "title": "Url",
      "default": "",
      "x-order": 1,
      "description": "URL to fetch and scan. Used only if `content` is empty."
    },
    "content": {
      "type": "string",
      "title": "Content",
      "default": "",
      "x-order": 0,
      "description": "MCP server / agent skill source code to scan. Leave empty if using `url` instead."
    },
    "max_bytes": {
      "type": "integer",
      "title": "Max Bytes",
      "default": 200000,
      "maximum": 2000000,
      "minimum": 1024,
      "x-order": 2,
      "description": "Maximum bytes to read from `url` (truncated, default 200000)."
    }
  }
}

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema

{
  "type": "object",
  "title": "Output"
}