80trust / 100

Proxy Pii Redact

by PII Redaction and Anonymization in Company & people data

x402 APIPassing, checked 3 h ago

PII redaction for agent pipelines: remove personal data from text before it goes to another model, a log, a ticket system or a dataset. Emails, IBANs (checksum verified), card numbers (Luhn verified), phone numbers and IP addresses are found by exact patterns; names of people, street addresses, birth dates and ID numbers by Claude Haiku 5.5.

POST https://agentsvc.io/api/v1/proxy/pii-redact

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
32 ms typical, 105 ms slowest 5%
Last check
3 h ago
Next check
any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://agentsvc.io/api/v1/proxy/pii-redact" \
  -H "content-type: application/json" \
  -d '{"text":"Hi, this is Anna Schulz from Berlin. Please refund order 4471 to DE89 3704 0044 0532 0130 00 and confirm to [email protected] or +49 30 1234 5678."}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fagentsvc.io%2Fapi%2Fv1%2Fproxy%2Fpii-redact
const res = await pay("https://agentsvc.io/api/v1/proxy/pii-redact", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"text":"Hi, this is Anna Schulz from Berlin. Please refund order 4471 to DE89 3704 0044 0532 0130 00 and confirm to [email protected] or +49 30 1234 5678."}),
});
console.log(await res.json());

Example input

{
  "text": "Hi, this is Anna Schulz from Berlin. Please refund order 4471 to DE89 3704 0044 0532 0130 00 and confirm to [email protected] or +49 30 1234 5678."
}

Example output

{
  "data": {},
  "success": true
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
3 h agoPassed402105 ms$0.003
6 h agoPassed40231 ms$0.003
10 h agoPassed402106 ms$0.003
14 h agoPassed40294 ms$0.003
17 h agoPassed402103 ms$0.003
21 h agoPassed40229 ms$0.003
24 h agoPassed40297 ms$0.003
29 h agoPassed40230 ms$0.003
32 h agoPassed40231 ms$0.003
35 h agoPassed40231 ms$0.003
40 h agoPassed40232 ms$0.003