ToolVet
75trust / 100

Services Agent Prehire Check

by api.craigmbrown.com in Security & trust

x402 APIPassing, checked 3 h ago

Pre-hire due-diligence check on an agent before you delegate it real spend authority: settlement history, dispute rate, and any flagged incidents, in one signed report. | BlindOracle by Craig M. Brown (craigmbrown.com) - counterparty-risk infrastructure sold to autonomous AI agents; self-built multi-agent framework (42+ agents); ERC-8004 agent passport #60979; paid via x402 in USDC on Base

POST
https://api.craigmbrown.com/v1/services/agent.prehire-check
Price
$0.25
per call in USDC
Uptime
100%
last 30 days
Response time
355 ms
515 ms slowest 5%
Last check
Passed
3 h ago, next any minute now

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed

How to call it

POST https://api.craigmbrown.com/v1/services/agent.prehire-check

Each call costs $0.25 in USDC on Base, 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.

POST https://api.craigmbrown.com/v1/services/agent.prehire-check
content-type: application/json

{
  "agent_name": "..."
}

Parameters

ParameterTypeRequiredDescription
agent_namestringNo
task_idstringNo
walletstringNo

Example response

The provider's example. We can't check it without paying.

{
  "audit_status": "...",
  "deliveries": 0,
  "first_seen": "...",
  "reasons": [],
  "red_flags": [],
  "verdict": "..."
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.25.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://api.craigmbrown.com/v1/services/agent.prehire-check' \
  -H 'content-type: application/json' \
  --data-raw '{"agent_name":"..."}'

# 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 - -X POST 'https://api.craigmbrown.com/v1/services/agent.prehire-check' \
  -H 'content-type: application/json' \
  --data-raw '{"agent_name":"..."}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: 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 $0.25 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.25" });
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 $0.25 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fapi.craigmbrown.com%2Fv1%2Fservices%2Fagent.prehire-check&method=POST
const res = await pay("https://api.craigmbrown.com/v1/services/agent.prehire-check", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "agent_name": "..."
  }),
});
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 $0.25 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.25"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://api.craigmbrown.com/v1/services/agent.prehire-check",
        json={
            "agent_name": "...",
        },
    )
    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

WhenResultHTTPTimePrice
3 h agoPassed402421 ms$0.25
7 h agoPassed402390 ms$0.25
12 h agoPassed402336 ms$0.25
16 h agoPassed402452 ms$0.25
20 h agoPassed402361 ms$0.25
Show 10 older checks
24 h agoPassed402546 ms$0.25
28 h agoPassed402480 ms$0.25
32 h agoPassed402261 ms$0.25
36 h agoPassed402355 ms$0.25
40 h agoPassed402351 ms$0.25
44 h agoPassed402515 ms$0.25
2 days agoPassed402180 ms$0.25
2 days agoPassed402434 ms$0.25
2 days agoPassed402353 ms$0.25
2 days agoPassed402376 ms$0.25