Leakguard Lite
by LeakGuard by AgentGate in Onchain & crypto
Secret and PII detection API (redact before sending to an LLM). Find and redact leaked secrets before an AI agent sends text to an LLM, tool or webhook: crypto seed phrases (BIP39 checksum), EVM/Solana private keys, WIF, xprv, API keys (GitHub, AWS, Stripe, OpenAI, Anthropic, Slack...), JWT, PEM, cards, IBAN, SSN, email, phone. Verdict, findings and redacted text.
https://api.youraitools.co/leakguard/v1/lite- Price
- $0.005
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 107 ms
- 161 ms slowest 5%
- Last check
- Passed
- 5 h ago, next any minute now
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
GET https://api.youraitools.co/leakguard/v1/lite
Each call costs $0.005 in USDC on Polygon, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
GET https://api.youraitools.co/leakguard/v1/lite?text=agent+log%3A+restored+wallet+from+seed+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+about%3B+aws+key+AKIAIOSFODNN7EXAMPLE%3B+contact+ops%40example.comParameters
| Parameter | Type | Required | Description |
|---|---|---|---|
min_severity | string | No | One of: low, medium, high, critical. |
style | string | No | label: [REDACTED:type] (default); mask: keep the last 4 digits / email domain for PII One of: label, mask. |
text | string | Yes | Text to check before it is sent (prompt, tool arguments, log, message, file content). POST /v1/scan also accepts {"json": <any JSON payload>}. |
types | string | No | Optional comma-separated finding types or categories to report (wallet_key, secret, pii, email, ...) |
Example response
The provider's example. We can't check it without paying.
Example response, 53 lines
{
"checked_at": "2026-10-22T19:07:15.225Z",
"confidence": "high",
"counts": {
"aws_access_key_id": 1,
"bip39_mnemonic": 1,
"email": 1
},
"engine": "leakguard-0.1.0 (leakguard-engine/0.1.0)",
"findings": [
{
"category": "wallet_key",
"confidence": 0.99,
"end": 130,
"preview": "[REDACTED:bip39_mnemonic]",
"remediation": "Treat the wallet as compromised: create a new seed offline and move all funds now. Never paste a seed phrase into a chat, prompt or tool.",
"severity": "critical",
"start": 37,
"type": "bip39_mnemonic",
"validator": "bip39 checksum ok (12 words)"
},
{
"category": "secret",
"confidence": 0.9,
"end": 160,
"preview": "[REDACTED:aws_access_key_id]",
"remediation": "Deactivate and rotate the access key in AWS IAM; check CloudTrail for use.",
"severity": "high",
"start": 140,
"type": "aws_access_key_id"
},
{
"category": "pii",
"confidence": 0.9,
"end": 185,
"preview": "o***@example.com",
"remediation": "Personal data: send only if the recipient needs it (data minimization).",
"severity": "medium",
"start": 170,
"type": "email"
}
],
"input": {
"bytes": 185,
"kind": "text"
},
"max_severity": "critical",
"redacted": "agent log: restored wallet from seed [REDACTED:bip39_mnemonic]; aws key [REDACTED:aws_access_key_id]; contact [REDACTED:email]",
"safe_to_send": false,
"sources_failed": [],
"tier": "lite",
"verdict": "WALLET_KEY_EXPOSED"
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.005.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i 'https://api.youraitools.co/leakguard/v1/lite?text=agent+log%3A+restored+wallet+from+seed+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+about%3B+aws+key+AKIAIOSFODNN7EXAMPLE%3B+contact+ops%40example.com'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - 'https://api.youraitools.co/leakguard/v1/lite?text=agent+log%3A+restored+wallet+from+seed+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+about%3B+aws+key+AKIAIOSFODNN7EXAMPLE%3B+contact+ops%40example.com' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.005 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.005" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.005 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fapi.youraitools.co%2Fleakguard%2Fv1%2Flite
const res = await pay("https://api.youraitools.co/leakguard/v1/lite?text=agent+log%3A+restored+wallet+from+seed+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+about%3B+aws+key+AKIAIOSFODNN7EXAMPLE%3B+contact+ops%40example.com");
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.005 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.005"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.get("https://api.youraitools.co/leakguard/v1/lite?text=agent+log%3A+restored+wallet+from+seed+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+abandon+about%3B+aws+key+AKIAIOSFODNN7EXAMPLE%3B+contact+ops%40example.com")
print(res.status_code, res.text)Security scan
No findings
We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 5 h ago | Passed | 402 | 95 ms | $0.005 |
| 13 h ago | Passed | 402 | 69 ms | $0.005 |
| 21 h ago | Passed | 402 | 104 ms | $0.005 |
| 28 h ago | Passed | 402 | 107 ms | $0.005 |
| 36 h ago | Passed | 402 | 156 ms | $0.005 |
Show 10 older checks
| 44 h ago | Passed | 402 | 35 ms | $0.005 |
| 2 days ago | Passed | 402 | 120 ms | $0.005 |
| 2 days ago | Passed | 402 | 110 ms | $0.005 |
| 3 days ago | Passed | 402 | 73 ms | $0.005 |
| 3 days ago | Passed | 402 | 34 ms | $0.005 |
| 3 days ago | Passed | 402 | 107 ms | $0.005 |
| 4 days ago | Passed | 402 | 45 ms | $0.005 |
| 4 days ago | Passed | 402 | 119 ms | $0.005 |
| 4 days ago | Passed | 402 | 161 ms | $0.005 |
| 4 days ago | Passed | 402 | 131 ms | $0.005 |