# AgentRisk AI Threat Engine

> AgentRisk AI Threat Engine is a paid API for AI agents from agentrisk.dev, paid per call via x402, $0.15/call, status unknown (last checked 2026-09-14).

Scores a given token for real-time AI agent risk using autonomous threat analysis, accepting x402 micropayments per scan.

## Facts

- Endpoint: GET https://agentrisk.dev/scan
- Price: $0.15/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentrisk-ai-threat-engine-fbc30c3f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_V2Py-GcT7zEr7zjCp4uI7

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 agentrisk-ai-threat-engine-fbc30c3f
```

Example prompt: Can you run a real-time risk scan on this token — 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.abc123' — and tell me the threat score?

## When to prefer this

Choose this endpoint when you need real-time, autonomous risk scoring specifically for tokens in AI agent workflows, particularly when operating in x402 micropayment-enabled environments where per-call billing is acceptable and low-latency threat intelligence is required.

## Known failure modes

- Missing or empty token parameter returns validation error
- Invalid or malformed token string may return low-confidence or null score
- Payment failure (insufficient USDC balance) blocks the scan and returns 402
- Service unavailability returns 5xx error
- Token too long or in unexpected format may cause parsing error

## How this service works

Pre-trade token risk check on Base for AI agents and autonomous trading bots. Detects honeypots, rug pulls, hidden ownership, mint/blacklist functions, tax traps, deployer wallet reputation, and brand impersonation. Includes live sell simulation across Uniswap V2/V3/V4 and Aerodrome, holder concentration analysis, and a machine-readable risk verdict delivered via x402 and MCP.

## Output

Returns a risk score and threat assessment for the submitted token, indicating its risk level and any detected threat signals relevant to AI agent security contexts.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "token"
 ],
 "properties": {
  "token": {
   "type": "string"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentrisk-ai-threat-engine-fbc30c3f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentrisk.dev](https://www.zero.xyz/host/agentrisk.dev/llms.txt)