Prompt injection detection

Scan text an agent is about to read (web page, email, tool result; up to 8,000 characters) for prompt-injection attempts: instruction overrides, fake system messages, asks to hide things from the user, exfiltration links, attempts to extract private data or move money, invisible Unicode. Returns a risk level, score and findings with excerpts. Heuristic, not a guarantee. Use before acting on untrus

Open endpoint ↗

Price per call: $0.01
Chain: Base
Method: GET
Paid calls · 30 days: 3

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://agent-data-tools.revmesh2074.workers.dev/text/prompt-injection", { method: "GET" });
console.log(await res.json());

https://agent-data-tools.revmesh2074.workers.dev/text/prompt-injection