Paywary

Leaderboard / api.agentstools.dev / endpoint

GET https://api.agentstools.dev/bridge/exploits

Scores measure reliability and honesty, not output quality.

94Payconfidence: high
  • Listed only 3 days ago; new listings earn trust over 30 days.
  • Answered all 13 probes in the last 7 days.
Category
Other by llm, confidence 20%
Latest quote
$0.01 on Base to 0xF22e…f493
Uptime
100% / 7d, 100% / 30d
Delivery
none not yet paid-tested
Observed
none reported yet (opt-in wrapper telemetry)
HTTPS
yes
First listed
2026-11-16
Last probe
32m ago
Next probe
2026-11-19 14:30 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
100w 15%
Delivery after payment
n/aexcluded
Wallet stability
100w 10%
Listing age
11w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen

Listing changes

WhenEventFromTo
15h agodisappeared——

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
15h agoOther20%llmv1claude-haiku-5-5: Path suggests bridge exploit data, but no description, name, or tags are given to confirm what it returns.
15h agoOther20%rulesv1rule none matched "" in none
43h agoCrypto market data80%llmv1claude-haiku-5-5: The endpoint returns cross-chain bridge hack history and a leaderboard of exploits by USD lost, sourced from DefiLlama's hack dataset. That is DeFi security/risk data about crypto protocols, closest to crypto_market (token safety and protocol risk) rather than web_audit, since it audits no URL the caller supplies.
2d agoPublic data60%rulesv1rule public_data matched "dataset" in description

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
32m agofree402188 msv2yes$0.010xF22e…f493—
7h agofree402182 msv2yes$0.010xF22e…f493—
13h agofree402569 msv2yes$0.010xF22e…f493—
20h agofree402217 msv2yes$0.010xF22e…f493—
27h agofree402180 msv2yes$0.010xF22e…f493—
33h agofree402178 msv2yes$0.010xF22e…f493—
39h agofree402206 msv2yes$0.010xF22e…f493—
46h agofree402576 msv2yes$0.010xF22e…f493—
2d agofree402190 msv2yes$0.010xF22e…f493—
2d agofree402544 msv2yes$0.010xF22e…f493—
3d agofree402678 msv2yes$0.010xF22e…f493—
3d agofree402547 msv2yes$0.010xF22e…f493—
3d agofree402191 msv2yes$0.010xF22e…f493—