# Agent Security Gateway - Batch Security Scan

> Agent Security Gateway - Batch Security Scan is a paid API for AI agents from agent-security-gateway.onrender.com, paid per call via x402, $0.1/call, status unknown (last checked 2026-09-15).

Batch-scans multiple content items for security threats including prompt injection, validates content safety, and returns risk scores with sanitized output for AI agents.

## Facts

- Endpoint: POST https://agent-security-gateway.onrender.com/api/security/batch
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-security-gateway-batch-security-scan-b9d29408
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_5fkM4j8ZpJAHuwWEMGJx-

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agent-security-gateway-batch-security-scan-b9d29408 -d '<json body>'
```

Example prompt: Before I process these 3 user messages, run a batch security scan on them to detect any prompt injection or threats — especially Japanese prompt injection — and tell me which ones are safe to use and what the risk scores are.

## When to prefer this

Use this endpoint when you need to security-check multiple content items in a single paid call rather than scanning one at a time; ideal for AI agents that receive batches of user inputs and need pre-processing threat assessment before acting on them, particularly when Japanese prompt injection is a concern.

## Known failure modes

- Empty or malformed contents array returns validation error
- Unsupported content_type may produce unexpected scan behavior
- Payment failure via x402/USDC halts the request before scanning
- Network timeout on large batches from Render.com cold starts
- False negatives on novel prompt injection patterns not yet in detection rules

## How this service works

Pay-per-request security APIs for autonomous AI agents using x402. Detect Japanese prompt injection, validate content, scan for threats, and perform pre-payment security checks. Built for USDC/Base payments.

## Output

Returns an array of per-item security scan results each containing a risk_score (integer), risk_level (string), threats_detected (list), safe_to_use (boolean), sanitized_content, and recommendations; plus a batch summary and a next_recommended API suggestion for further security analysis.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "contents"
 ],
 "properties": {
  "contents": {
   "type": "array"
  },
  "content_type": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object",
 "title": "BatchScanResponse",
 "required": [
  "results",
  "summary",
  "next_recommended"
 ],
 "properties": {
  "results": {
   "type": "array",
   "items": {
    "type": "object",
    "title": "SecurityScanResponse",
    "required": [
     "risk_score",
     "risk_level",
     "threats_detected",
     "safe_to_use",
     "recommendations",
     "sanitized_content",
     "next_recommended"
    ],
    "properties": {
     "risk_level": {
      "type": "string",
      "title": "Risk Level"
     },
     "risk_score": {
      "type": "integer",
      "title": "Risk Score"
     },
     "safe_to_use": {
      "type": "boolean",
      "title": "Safe To Use"
     },
     "recommendations": {
      "type": "array",
      "items": {
       "type": "string"
      },
      "title": "Recommendations"
     },
     "next_recommended": {
      "type": "object",
      "title": "NextRecommendation",
      "required": [
       "api_name",
       "url",
       "reason",
       "expected_improvement",
       "price_usdc"
      ],
      "properties": {
       "url": {
        "type": "string",
        "title": "Url"
       },
       "reason": {
        "type": "string",
        "title": "Reason"
       },
       "api_name": {
        "type": "string",
        "title": "Api Name"
       },
       "price_usdc": {
        "type": "number",
        "title": "Price Usdc"
       },
       "expected_improvement": {
        "type": "string",
        "title": "Expected Improvement"
       }
      }
     },
     "threats_detected": {
      "type": "array",
      "items": {
       "type": "string"
      },
      "title": "Threats Detected"
     },
     "sanitized_content": {
      "type": "string",
      "title": "Sanitized Content"
     }
    }
   },
   "title": "Results"
  },
  "summary": {
   "type": "object",
   "title": "Summary",
   "additionalProperties": true
  },
  "next_recommended": {
   "type": "object",
   "title": "NextRecommendation",
   "required": [
    "api_name",
    "url",
    "reason",
    "expected_improvement",
    "price_usdc"
   ],
   "properties": {
    "url": {
     "type": "string",
     "title": "Url"
    },
    "reason": {
     "type": "string",
     "title": "Reason"
    },
    "api_name": {
     "type": "string",
     "title": "Api Name"
    },
    "price_usdc": {
     "type": "number",
     "title": "Price Usdc"
    },
    "expected_improvement": {
     "type": "string",
     "title": "Expected Improvement"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-security-gateway-batch-security-scan-b9d29408/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-security-gateway.onrender.com](https://www.zero.xyz/host/agent-security-gateway.onrender.com/llms.txt)