# Crypto Scam Message Detector

> Crypto Scam Message Detector is a paid API for AI agents from agentsvc.io, paid per call via x402, $0.003/call, status unknown (last checked 2026-10-11).

Analyzes text messages (DMs, tweets, emails, comments) for crypto-related scams and phishing, returning a verdict, risk score, scam type, and red flags.

## Facts

- Endpoint: POST https://agentsvc.io/api/v1/proxy/scam-message-check?utm_source=zero.xyz
- Price: $0.003/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/crypto-scam-message-detector-46b267d4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vAqaSKXAvfkzKrif-Ywdx

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 crypto-scam-message-detector-46b267d4 -d '<json body>'
```

Example prompt: Can you check this DM I got on X from @CryptoSupport99: 'Congratulations! Your wallet has been selected for a 2 ETH airdrop. Connect your wallet at airdrop-claim.xyz to receive your funds.' Is it a scam?

## When to prefer this

Choose this endpoint when an agent or application needs real-time, crypto-specific scam classification before a user or bot acts on an incoming message. It is purpose-built for crypto contexts (wallet drainers, seed phrase theft, fake airdrops, pig butchering) rather than generic spam filters, making it superior for crypto wallets, trading bots, and social agents operating in Web3 environments.

## Known failure modes

- Text exceeds 8,000 character limit — request rejected
- Empty or missing text field — returns validation error
- Ambiguous message with no clear scam signals may return 'safe' verdict with low confidence
- Very short or context-free messages may yield imprecise scam_type classification
- Network or upstream model errors may return 5xx response

## How this service works

Scam and phishing detection for crypto wallets, trading bots and social agents: check a DM, cast, tweet, email or comment before your agent or user acts on it. Returns a verdict safe, suspicious or scam, a 0 to 100 risk score, the scam type (wallet drainer, fake airdrop, phishing login, impersonation, seed phrase theft, fake support, giveaway doubling, investment fraud, pig butchering, malware), red flags with exact quotes, and advice.

## Output

Returns a JSON object with: verdict (safe, suspicious, or scam), risk_score (0–100 integer), scam_type (one of: wallet drainer, fake airdrop, phishing login, impersonation, seed phrase theft, fake support, giveaway doubling, investment fraud, pig butchering, malware), an array of red_flags with exact quoted text from the message, and actionable advice for the user or agent.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "The message to check, max 8,000 chars"
  },
  "sender": {
   "type": "string",
   "description": "Optional: sender name or handle as shown, max 200 chars"
  },
  "channel": {
   "type": "string",
   "description": "Optional: where it arrived, e.g. X DM, Telegram, Discord, email"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/crypto-scam-message-detector-46b267d4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentsvc.io](https://www.zero.xyz/host/agentsvc.io/llms.txt)