Incidents Exposure
by tensorfeed.ai in Developer tools
AI safety incident exposure analytics. Per-developer and per-deployer incident counts with recency-weighted exposure_score (1.0 last 30d, 0.5 days 31-90, 0.25 older), risk_domain and SEP-view (Security/Ethics/Performance) distributions, top affected artifacts. Derived over the AVID (avidml/avid-db, MIT) snapshot refreshed daily. The "which AI vendors have the most recent reported safety incidents" call.
https://tensorfeed.ai/api/premium/ai-safety/incidents/exposure- Price
- $0.02
- per call in USDC
- Uptime
- 100%
- last 30 days
- Response time
- 435 ms
- 660 ms slowest 5%
- Last check
- Passed
- 3 h ago, next any minute now
Reliability
Status and outage history · Atom feed · Watch with other listings
How to call it
GET https://tensorfeed.ai/api/premium/ai-safety/incidents/exposure
Each call costs $0.02 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.
GET https://tensorfeed.ai/api/premium/ai-safety/incidents/exposure?risk_domain=Security&vendor=OpenAI&within_days=90Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
risk_domain | string | No | Case-insensitive substring match against AVID risk_domains (Security, Ethics, Performance, ...). |
vendor | string | No | Case-insensitive substring match against developer + deployer + artifact name. |
within_days | integer | No | Restrict to incidents reported in the last N days. Omit for full snapshot. |
Example response
The provider's example. We can't check it without paying.
Example response, 60 lines
{
"billing": {
"credits_charged": 1,
"credits_remaining": 49
},
"capturedAt": "2026-05-24T12:00:00Z",
"deployers": [],
"developers": [
{
"exposure_score": 5.5,
"incident_count": 8,
"latest_report_id": "AVID-2026-R0481",
"latest_reported_date": "2026-05-18",
"recent_count_30d": 2,
"risk_domains": [
"Ethics",
"Security"
],
"role": "developer",
"vendor": "OpenAI"
}
],
"entries_count": 12,
"filter": {
"risk_domain": "Security",
"vendor": "OpenAI",
"within_days": 90
},
"ok": true,
"risk_domains": [
{
"incident_count": 8,
"recent_count_30d": 2,
"risk_domain": "Security"
}
],
"sep_view": [
{
"incident_count": 4,
"sep_view": "S0403: Adversarial Example"
}
],
"snapshot_captured_at": "2026-05-24T03:00:00Z",
"source": "avidml/avid-db",
"source_license": "MIT",
"top_artifacts": [
{
"developers": [
"OpenAI"
],
"incident_count": 3,
"name": "gpt-4o",
"type": "Model"
}
],
"window": {
"cutoff_date": "2026-02-23",
"window_days": 90
}
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.02.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i 'https://tensorfeed.ai/api/premium/ai-safety/incidents/exposure?risk_domain=Security&vendor=OpenAI&within_days=90'
# 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://tensorfeed.ai/api/premium/ai-safety/incidents/exposure?risk_domain=Security&vendor=OpenAI&within_days=90' \
| 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 $0.02 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.02" });
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 $0.02 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Ftensorfeed.ai%2Fapi%2Fpremium%2Fai-safety%2Fincidents%2Fexposure
const res = await pay("https://tensorfeed.ai/api/premium/ai-safety/incidents/exposure?risk_domain=Security&vendor=OpenAI&within_days=90");
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 $0.02 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.02"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.get("https://tensorfeed.ai/api/premium/ai-safety/incidents/exposure?risk_domain=Security&vendor=OpenAI&within_days=90")
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 |
|---|---|---|---|---|
| 3 h ago | Passed | 402 | 308 ms | $0.02 |
| 7 h ago | Passed | 402 | 259 ms | $0.02 |
| 12 h ago | Passed | 402 | 234 ms | $0.02 |
| 17 h ago | Passed | 402 | 273 ms | $0.02 |
| 21 h ago | Passed | 402 | 460 ms | $0.02 |
Show 10 older checks
| 26 h ago | Passed | 402 | 321 ms | $0.02 |
| 30 h ago | Passed | 402 | 398 ms | $0.02 |
| 34 h ago | Passed | 402 | 365 ms | $0.02 |
| 38 h ago | Passed | 402 | 616 ms | $0.02 |
| 43 h ago | Passed | 402 | 1.1 s | $0.02 |
| 47 h ago | Passed | 402 | 211 ms | $0.02 |
| 2 days ago | Passed | 402 | 342 ms | $0.02 |
| 2 days ago | Passed | 402 | 655 ms | $0.02 |
| 3 days ago | Passed | 402 | 477 ms | $0.02 |
| 3 days ago | Passed | 402 | 571 ms | $0.02 |