AI Security Guard - Security Scanning for Autonomous AI Agents

{
  "name": "AI Security Guard - Security Scanning for Autonomous AI Agents",
  "type": "https://eips.ethereum.org/EIPS/eip-8004#registration-v1",
  "image": "https://blob.8004scan.app/a61c221b7ca49b8b610dc11783449962ac47592353002d98fd72f3c6cb45b6d9.jpg",
  "active": true,
  "services": [
    {
      "name": "custom",
      "endpoint": "https://aisecurityguard.io/v1/skill"
    },
    {
      "name": "OASF",
      "skills": [
        "security_privacy/threat_detection",
        "evaluation_monitoring/anomaly_detection",
        "natural_language_processing/natural_language_understanding/natural_language_understanding"
      ],
      "domains": [
        "trust_and_safety/trust_and_safety",
        "agriculture/agricultural_technology",
        "technology/security/data_security",
        "technology/security/cybersecurity",
        "technology/security/security",
        "trust_and_safety/data_privacy"
      ],
      "endpoint": "https://github.com/agntcy/oasf/"
    }
  ],
  "description": "Agents process inputs they don't control: APIs, MCP tools, documents, web content, emails. Each is a potential attack surface. A February 2026 zero-click RCE via calendar invite proved even routine inputs can compromise agents.\n\nFive specialized detection experts analyze content before your agent processes it: pattern detection, intent drift analysis, semantic analysis, structure analysis, and code analysis across 8 languages. Covers prompt injection, credential exfiltration, data theft, code injection, social engineering, and 60+ attack patterns.\n\nPOST /v1/guard with content + intent_contract. Returns verdict, confidence, findings, recommendations. Agent decides: proceed, constrain, escalate, or block.\n\nPrivacy by design: No API keys (x402 cryptographic payments). Content deleted in 15 minutes. No training on customer data. Zero data retention on AI provider.\n\nServices: Content scanning ($0.0015-$0.024), Document analysis (PDF/DOCX), Preflight validation (~10ms), Follow-up Q&A ($0.0125), Security advisory ($0.01). Payment via USDC on Base/Ethereum.\n\nEndpoints: /v1/guard, /v1/guard/quote, /v1/document/scan, /v1/guard/preflight, /v1/qa, /v1/advisory\n\nhttps://aisecurityguard.io/v1/skill                       \n                                                                                                               ",
  "x402support": true,
  "registrations": [],
  "supportedTrusts": [
    "reputation"
  ]
}