# Scam & Phishing Message Filter

> Scam & Phishing Message Filter is a paid API for AI agents from api.fadeandco.workers.dev, paid per call via x402, $0.002/call, status unknown (last checked 2026-10-29).

Screens a text message for crypto and phishing scam signals (urgency, fake support, wallet/seed-phrase requests, guaranteed returns, suspicious links) and returns a HIGH/MEDIUM/LOW/NONE risk rating with matched phrases.

## Facts

- Endpoint: POST https://api.fadeandco.workers.dev/api/agent-intel/scam-phishing-message-filter?utm_source=zero.xyz
- Price: $0.002/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-29
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/scam-phishing-message-filter-3f668ce7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_3ukd3LnX_GU7VUQlZQ_NE

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 scam-phishing-message-filter-3f668ce7 -d '<json body>'
```

Example prompt: Can you screen this DM I just received for scam signals: 'Congratulations! Your wallet has been selected for a 2 ETH airdrop — connect your wallet now at claim-eth.io to verify. This offer expires in 10 minutes!'?

## When to prefer this

Use this endpoint when you need a fast, lightweight, rule-based first-pass filter for English crypto and phishing scam messages — ideal for agent inbox triage, automated DM screening, or alerting users before they interact with suspicious content. Prefer this over LLM-based analysis when you need deterministic, auditable signal with known matched phrases and consistent latency. Do not use it as a sole trust signal, and note it will miss novel phrasing or non-English scams.

## Known failure modes

- Message text missing or empty — API likely returns a validation error
- Message exceeds 10,000 character limit — will be rejected
- New or novel scam wording not in the fixed rule list — returns NONE even if malicious
- Non-English messages — rule list is English-only, non-English scams may return NONE
- No account/sender context available — cannot assess sender reputation, only message text

## How this service works

Screens one message (DM, email or chat text) for common crypto and phishing scam signals in English: urgency, fake support or giveaway, wallet-connect or seed-phrase requests, guaranteed returns, and suspicious links. Returns HIGH/MEDIUM/LOW/NONE with each matched phrase. A fixed rule list: it misses new wording and other languages, and it never sees the sender's account.

## Output

A JSON object containing a risk field (HIGH, MEDIUM, LOW, or NONE), a matches array listing each matched suspicious phrase, a checkedAt ISO timestamp, a source field identifying the rule set used, and a note reminding the caller that NONE means no known pattern was matched, not that the sender is trustworthy.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "description": "The message to screen, 1 to 10000 characters"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "note": "Fixed English rule list. NONE means no known pattern, not that the sender is trustworthy.",
  "risk": "NONE",
  "source": "hand-written rule list",
  "matches": [],
  "checkedAt": "2026-10-23T22:05:51.000Z"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/scam-phishing-message-filter-3f668ce7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.fadeandco.workers.dev](https://www.zero.xyz/host/api.fadeandco.workers.dev/llms.txt)