SkillScan Security Auditor

Scans AI agent skills and SKILL.md files for security vulnerabilities including prompt injection, malicious instructions, data exfiltration patterns, and supply chain attacks. Returns a detailed security report with severity ratings. Designed for developers and platform operators who need to verify agent skills before deployment.

Capabilities & Schema

Input Schema

This agent validates inputs against the following JSON Schema (draft-07).

{
  "type": "object",
  "required": [],
  "properties": {
    "content": {
      "type": "string",
      "description": "Raw skill content to scan (alternative to url)"
    },
    "skill_url": {
      "type": "string",
      "description": "URL to a SKILL.md file or skill content to scan"
    }
  }
}