Paywary

Leaderboard / aisecurityguard.io / endpoint

POST http://aisecurityguard.io/v1/guard

Scores measure reliability and honesty, not output quality.

79Payconfidence: medium
  • Quoted a price different from the listed price on 10 of 10 comparable probes.
  • Served over plain HTTP, so payment details can be tampered with in transit.
Category
Other by llm, confidence 10%
Latest quote
$0.0095 on Base to 0x4B16…71d2
Uptime
100% / 7d, 100% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
no
First listed
2026-11-16
Last probe
2h ago
Next probe
2026-11-19 00:57 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
50w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
9w 5%
HTTPS
0w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
payaiexactBase0x8335…2913$0.00150x4B16…71d2defaultyes4h ago

Paid probes

No paid probes yet. Paid probing is off by default and runs weekly per host under a strict spend cap; each paid probe links to its on-chain transaction here.

Delivery checks

Inside each paid probe we ask for something whose correct answer we know, then compare. A pass means the seller delivered what it was paid for; a fail means it charged and returned something wrong; inconclusive means we could not judge (no reference, unknown input shape, or a non-2xx response). Every row carries the request, the response hash and the reference so the verdict can be reproduced. Judged results feed the "Delivery after payment" component (pass 1, error after payment 0.25, fail 0); inconclusive rows are excluded; a fail in the last 14 days caps the verdict at caution. Methodology.

No delivery checks yet. They run inside the weekly paid probe.

Classification history

Every classification is kept; the newest row is the current category. Rules match the listing text; the model is consulted only when the rules are unsure.

WhenCategoryConfidenceMethodVersionEvidence
16h agoOther10%llmv1claude-haiku-5-5: Host name suggests AI security screening, but no description, tags or examples are given to confirm what the endpoint returns.
2d agoOther20%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
2h agofree402371 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
10h agofree402361 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
16h agofree402202 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
22h agofree402205 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
29h agofree402219 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
35h agofree402212 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
42h agofree402203 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
2d agofree402407 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
2d agofree402375 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch
3d agofree402205 msv2yes$0.00950x4B16…71d2http_not_httpsprice_above_listingprice_mismatch