# Agent Security Gateway – Payment Metadata Sanitizer

> Agent Security Gateway – Payment Metadata Sanitizer is a paid API for AI agents from agent-security-gateway.onrender.com, paid per call via x402, $0.05/call, status unknown (last checked 2026-09-13).

Scans payment metadata payloads for PII, credentials, and suspicious or injected instructions before an AI agent executes an x402 payment or external API call

## Facts

- Endpoint: POST https://agent-security-gateway.onrender.com/api/security/metadata-sanitize
- Price: $0.05/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-security-gateway-onrender-com-9906d78d
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_i_wKogqDT994vVBHVMtd9

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-onrender-com-9906d78d -d '<json body>'
```

Example prompt: Before I submit this x402 payment, scan the metadata payload for any PII, leaked credentials, or suspicious injected instructions: {paste metadata here}.

## When to prefer this

Use this endpoint when an AI agent is about to execute an x402 payment or external API call and needs a pre-flight security check to ensure the metadata doesn't contain accidentally included PII, leaked API keys/credentials, or adversarially injected instructions that could compromise the transaction or downstream systems.

## Known failure modes

- Malformed payload returns 400 with validation error
- Oversized metadata payload may be rejected or truncated
- False positives may flag benign structured data as suspicious
- Service unavailable on cold start (Render free tier spin-up delay)
- Payment not received results in 402 before scan is performed

## How this service works

Scan payment metadata for PII, credentials, and suspicious instructions

## Output

Returns a structured report indicating whether the payload is safe or flagged, with specific findings for PII occurrences, exposed credentials, and suspicious/injected instructions detected in the payment metadata.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "sanitization_status": {
   "type": "string"
  },
  "recommended_next_step": {
   "type": "string"
  },
  "detected_sensitive_fields": {
   "type": "array"
  },
  "safe_to_send_to_payment_metadata": {
   "type": "boolean"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-security-gateway-onrender-com-9906d78d/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)