Review External

Last 30 days

Uptime

100%

Response time

591 ms typical, 736 ms slowest 5%

Last check

36 min ago

Next check

any minute now

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://api.babyblueviper.com/review/external" \
  -H "content-type: application/json" \
  -d '{"artifact":"Pay 0.02 USDC on Base for one market-data call; the payout address matches the listing.","artifact_type":"plan"}'

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%2Fapi.babyblueviper.com%2Freview%2Fexternal
const res = await pay("https://api.babyblueviper.com/review/external", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"artifact":"Pay 0.02 USDC on Base for one market-data call; the payout address matches the listing.","artifact_type":"plan"}),
});
console.log(await res.json());

Example input

{
  "artifact": "Pay 0.02 USDC on Base for one market-data call; the payout address matches the listing.",
  "artifact_type": "plan"
}

Example output

{
  "confidence": 0.88,
  "issues": [
    {
      "detail": "…",
      "severity": "high"
    }
  ],
  "proof": {
    "event": {
      "id": "<nostr id>",
      "sig": "<schnorr>"
    },
    "proof_payload": {
      "schema": "invinoveritas.verdict_proof.v1",
      "verifier_pubkey": "<x-only hex>",
      "verify_url": "https://api.babyblueviper.com/verify-proof"
    },
    "verify": "POST this proof's event to /verify-proof — anyone confirms we issued this verdict without trusting the presenter or us. Track record: /ledger."
  },
  "summary": "Safe to proceed; two non-blocking concerns noted.",
  "verdict": "approve_with_concerns"
}

Security scan

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

Recent checks