Agent Tools

Screen fetched text before your agent acts on it: JSON body {text} (max 50,000 chars). Rules for instruction override, role hijack, prompt leaks, fake system tags, data-exfiltration links, hidden Unicode and base64 payloads in 6 languages. Returns safe, suspicious or malicious, a 0-100 score and matched spans. Text is not stored.

Open endpoint ↗

Price per call: $0.005
Chain: Base
Method: POST
Paid calls · 30 days: 0

Call it from code

This API is run by its own provider and paid directly through x402. We list it so you can find it; we don't route or hold the payment.

import { x402Client, wrapFetchWithPayment } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";

const client = new x402Client();
registerExactEvmScheme(client, { signer: agentAccount });

const pay = wrapFetchWithPayment(fetch, client);
const res = await pay("https://agents.crowdspark.me/v1/text/injection-check", { method: "POST" });
console.log(await res.json());

https://agents.crowdspark.me/v1/text/injection-check