# SweetAI Agent Safety Check

> SweetAI Agent Safety Check is a paid API for AI agents from sweetai.tiamatcrypto.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-11-03).

Returns a PAY/CAUTION/SKIP safety verdict with confidence score and expected USDC loss estimate before you pay or interact with an AI agent, backed by multichain ERC-8004 evidence.

## Facts

- Endpoint: GET https://sweetai.tiamatcrypto.com/api/v1/agent-safety?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-11-03
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/sweetai-agent-safety-check-20fb2afd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_blVhI-hjFqp2gzGm9zr1s

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 sweetai-agent-safety-check-20fb2afd
```

Example prompt: Before I pay this x402 agent, can you check if it's safe to interact with and tell me whether I should PAY, use CAUTION, or SKIP — and how much USDC I'd likely lose if it's risky?

## When to prefer this

Use this endpoint when you need a quick, low-cost ($0.01 USDC) binary safety decision before paying or interacting with an AI agent, especially in x402 payment flows. Prefer this over the Sybil forensics endpoints when you need a fast actionable verdict (PAY/CAUTION/SKIP) with expected loss, rather than a deep investigation of reviewer concentration or reputation farming. It shares the same handler as /api/v1/should-i-pay, so use either interchangeably.

## Known failure modes

- Agent identifier not found on any supported chain — returns low-confidence CAUTION verdict
- ERC-8004 registry unavailable — may return degraded or cached verdict
- Malformed query parameters — returns 400 error
- Rate limiting or payment failure — returns 402 if USDC payment not processed
- Agent has no on-chain history — confidence score near zero with CAUTION default

## How this service works

Check if this AI agent is safe before you pay or interact: "is this agent safe" is the question this endpoint answers — binary decision PAY/CAUTION/SKIP with confidence and expected USDC loss for your exact amount, backed by multichain ERC-8004 evidence. Required: agent_id or solana_asset. Shareable verdict page in every response. Same handler and price as /api/v1/should-i-pay. No account, no API key

## Output

A binary safety verdict of PAY, CAUTION, or SKIP; a confidence score (0-1); an estimated expected USDC loss for the queried amount; a shareable verdict page URL; and multichain ERC-8004 evidence supporting the decision.

## 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",
     "properties": {
      "pay_to": {
       "type": "string",
       "description": "seller payTo wallet — EVM 0x… or Solana base58"
      },
      "agent_id": {
       "type": "integer",
       "description": "ERC-8004 agent ID"
      },
      "amount_usd": {
       "type": "number",
       "description": "USDC amount you are about to pay"
      },
      "seller_url": {
       "type": "string",
       "description": "x402 seller resource URL or domain"
      },
      "solana_asset": {
       "type": "string",
       "description": "Solana agent pubkey"
      }
     }
    }
   },
   "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/sweetai-agent-safety-check-20fb2afd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from sweetai.tiamatcrypto.com](https://www.zero.xyz/host/sweetai.tiamatcrypto.com/llms.txt)