Nanomind Security Classifier

{
  "agent_id": "nanomind_security_classifier",
  "name": "Nanomind Security Classifier",
  "url": "https://huggingface.co/opena2a/nanomind-security-classifier",
  "logo": "https://agentery.com/logos/CP-J8RSGD-256.png",
  "niche": "mcp-security-platform",
  "category": "security",
  "short_summary": "classifies AI agent configuration text (SKILL.md, MCP server configs, SOUL.md governance docs, tool descriptions) into 10 security threat categories",
  "task_performed": "classifies AI agent configuration text (SKILL.md, MCP server configs, SOUL.md governance docs, tool descriptions) into 10 security threat categories",
  "inputs_accepted": [
    "text content of AI agent configurations (MCP server configs",
    "SKILL.md",
    "SOUL.md docs",
    "tool descriptions)",
    "tokenized input_ids"
  ],
  "outputs_produced": [
    "threat classification label with confidence score (one of 10 categories e.g. exfiltration",
    "injection",
    "benign)"
  ],
  "integrations_available": [
    "HackMyAgent",
    "OpenA2A CLI",
    "ONNX Runtime",
    "MLX",
    "MCP",
    "Python",
    "Node.js"
  ],
  "protocols_or_interfaces": [
    "A2A",
    "MCP"
  ],
  "industry_fit": [
    "AI agent security / threat detection"
  ],
  "autonomy_level": "infrastructure",
  "human_approval_needed": "always required",
  "pricing_model": "free",
  "price": {
    "observed": false,
    "billing": "not_found",
    "currency": null,
    "lowest_monthly_usd": null,
    "monthly_usd": null,
    "headline": "No public price found",
    "summary": "No public pricing information is shown for the NanoMind Security Classifier model page.",
    "confidence": "medium",
    "source_url": "https://huggingface.co/opena2a/nanomind-security-classifier",
    "checked_at": "2026-10-28T02:33:40.273Z",
    "source_kind": "vendor",
    "amount": null,
    "display": null,
    "plans": [],
    "source": "render+llm"
  },
  "trust_or_rating_signal": [
    "Eval accuracy 98.45%",
    "Macro F1 0.9778",
    "Apache-2.0 license",
    "GitHub repository",
    "documented training corpus and benchmarks (OASB, DVAA, AgentPwn)"
  ],
  "evidence_quality": "high",
  "entity_type": "infrastructure",
  "regulated_data_suitability": "unclear",
  "evidence_urls": [
    "https://huggingface.co/opena2a/nanomind-security-classifier",
    "https://github.com/opena2a-org/agent-identity-management"
  ],
  "last_checked": "2026-10-28",
  "profile_checked": "2026-06-16",
  "price_checked": "2026-10-28",
  "how_to_connect": {
    "website": "https://huggingface.co/opena2a/nanomind-security-classifier",
    "docs": "https://github.com/docs",
    "mcp": null,
    "a2a": null,
    "api": {
      "docs_url": "https://huggingface.co/developer",
      "endpoint": null
    },
    "protocols": [],
    "install": null,
    "repository": null
  },
  "deployment": {
    "model": "unknown",
    "both_offered": false,
    "hosted_endpoint": null,
    "install": null,
    "note": "No deployment evidence held — Agentery has no endpoint, install instruction or directory attribute for this listing.",
    "evidence": null
  },
  "licence": {
    "name": null,
    "note": "No named licence found in the retained page text or source attributes. A public repository alone does not establish an open-source licence.",
    "evidence": null
  },
  "evidence_checks": {
    "price": {
      "status": "unknown",
      "note": "no observed price page text held for this listing"
    },
    "agent_card": {
      "status": "unknown",
      "note": "no Agent Card URL recorded for this listing"
    },
    "endpoint": {
      "status": "unknown",
      "note": "endpoint not yet checked"
    }
  },
  "product_group": null,
  "liveness": {
    "probed": true,
    "alive": true,
    "endpoint_kind": "site",
    "latency_ms": 174,
    "uptime_7d": 1,
    "checked_at": "2026-10-28T02:41:11.233Z",
    "consecutive_failures": 0,
    "status": "alive"
  },
  "price_extras": {
    "free_tier": null,
    "unit_cost": null
  },
  "reported_success": null,
  "feedback": "If you actually use this provider, call report_outcome with the result. Testing Agentery's connection or retrieval is not provider use and is stored unweighted."
}