# x-402 Input Guard — AI Agent Content Safety Scanner

> x-402 Input Guard — AI Agent Content Safety Scanner is a paid API for AI agents from api.x-402.online, paid per call via x402, $0.012/call, status unknown (last checked 2026-09-13).

Scans URLs or text content an AI agent is about to process for prompt-injection, data-exfiltration beacons, phishing, scam/wallet-drainer intent, and hidden steganographic unicode before the agent acts on it.

## Facts

- Endpoint: GET https://api.x-402.online/v1/guard
- Price: $0.012/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/x-402-input-guard-ai-agent-content-safety-scanner-185971c7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_sq0YXvHfWizKHIazk_rPM

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 x-402-input-guard-ai-agent-content-safety-scanner-185971c7
```

Example prompt: Before you open that link the user just sent me, scan it first with the x-402 guard — check the URL for prompt injection, phishing, wallet-drainer intent, and any hidden unicode tricks, then tell me if it's safe to proceed.

## When to prefer this

Choose this endpoint when your AI agent is about to consume untrusted external content — especially URLs, user-submitted links, or third-party data — and you need a pre-flight safety check specifically designed for AI agent threat vectors like prompt injection, markdown beacons, steganographic unicode, and crypto scam intent. Prefer this over generic URL reputation checkers when the threat model centers on adversarial AI inputs rather than just malware or spam.

## Known failure modes

- Missing required 'input' parameter returns validation error
- Non-HTTP input type rejected since only 'http' type with GET method is supported
- Malformed URL may return parsing error or inconclusive result
- Payment failure (insufficient USDC balance) returns 402 Payment Required
- Timeout on slow or unreachable URLs may return incomplete scan result

## How this service works

Input firewall for AI agents. Scan any UNTRUSTED content or URL an agent is about to read/act on, BEFORE it does. Detects prompt-injection, data-exfiltration (incl. markdown-image beacons), phishing, scam/wallet-drainer intent, and hidden/steganographic unicode — via determini…

## Output

A safety verdict indicating whether the scanned URL or content contains threats such as prompt-injection payloads, data-exfiltration attempts (including markdown image beacons), phishing indicators, scam or wallet-drainer intent, or hidden/steganographic unicode characters, along with specific risk flags for each detected threat category.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {}
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/x-402-input-guard-ai-agent-content-safety-scanner-185971c7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.x-402.online](https://www.zero.xyz/host/api.x-402.online/llms.txt)