MCPLow riskUnclaimed

Agent Skill & Config Security Audit

Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.

tylerscomic-labtylerscomic-lab/agent-skill-audit-mcpUpdated Oct 1, 2026

server.json

{
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "name": "io.github.tylerscomic-lab/agent-skill-audit-mcp",
  "description": "Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.",
  "title": "Agent Skill & Config Security Audit",
  "repository": {
    "url": "https://github.com/tylerscomic-lab/agent-skill-audit-mcp",
    "source": "github"
  },
  "version": "1.0.0",
  "remotes": [
    {
      "type": "streamable-http",
      "url": "https://agent-skill-audit-mcp.mcpize.run/mcp"
    }
  ]
}

Permissions

DeclaredDetected
Runs code—None
Installs—None
Runs install scripts—None
Networkagent-skill-audit-mcp.mcpize.runagent-skill-audit-mcp.mcpize.run
Needs credentialsNoneNone
Outside the workspace—None
Agent tools—None

Checks

Low risk · Nothing worth a warning was found.

Not reviewed by a person · Checked by rules; the model review is not switched on yet.

Versions

  1. #11.0.0latestOct 7, 2026