# Agent Guard Wallet Risk Scorer

> Agent Guard Wallet Risk Scorer is a paid API for AI agents from agent-guard.annushka1190.workers.dev, paid per call via x402, $0.025/call, status unknown (last checked 2026-09-14).

Deep risk scores a crypto wallet address (Base/Solana) before an agent sends a payment, returning a 0-1 riskScore, label, flags, and a safe_to_pay/review/avoid recommendation.

## Facts

- Endpoint: POST https://agent-guard.annushka1190.workers.dev/v1/wallet/risk-score
- Price: $0.025/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-guard-wallet-risk-scorer-08efefc3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_RMUTJRp2KBMuPXgeZMZfk

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-guard-wallet-risk-scorer-08efefc3 -d '<json body>'
```

Example prompt: Before you send that 50 USDC payment, can you risk-score the Base wallet 0x4f4C15d9bD7c796A9f9B769b78323EA3E0054104 and tell me if it's safe to pay or if I should avoid it?

## When to prefer this

Choose this endpoint when an AI agent needs a real-time, pre-payment trust decision for a specific wallet on Base (EVM) or Solana networks. It is purpose-built for autonomous agent payment flows requiring a structured safe_to_pay/review/avoid signal, rather than raw on-chain data. Prefer it over generic blockchain explorers when you need an aggregated risk label and actionable recommendation without implementing custom heuristics yourself.

## Known failure modes

- Invalid or malformed wallet address returns error or high-risk flag
- Unsupported blockchain network may return an error
- Newly created wallets with no on-chain history may return limited metrics and elevated risk score
- RPC node timeouts for on-chain lookups may cause delayed or failed responses
- Address exists on wrong chain (e.g. EVM address submitted for Solana) returns validation error

## How this service works

Safety and trust layer for AI agents: PII redaction, scam/phishing text scan, EVM/Solana address validation, IBAN checks, JSON repair, deep on-chain wallet risk scoring, x402 counterparty endpoint reputation checks. Free discovery: /openapi.json, /.well-known/x402, /v1/capabilities, /mcp (tools/list). REST + MCP. Pay with USDC via x402 — no API keys.

## Output

Returns a JSON object containing: riskScore (float 0-1), label (low/medium/high/critical), recommendation (safe_to_pay/review/avoid), an array of flags describing specific risk signals (e.g. zero activity, vanity pattern, contract detected), and a metrics object with txCount, ethBalance/solBalance, usdcBalance, isContract, and recentTxCount. For Solana, also includes recent signature counts and USDC token account presence.

## 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",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "address"
     ],
     "properties": {
      "address": {
       "type": "string",
       "description": "Wallet address"
      },
      "network": {
       "type": "string",
       "description": "base | solana (default base)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "ok": true
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-guard-wallet-risk-scorer-08efefc3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-guard.annushka1190.workers.dev](https://www.zero.xyz/host/agent-guard.annushka1190.workers.dev/llms.txt)