Paywary

Leaderboard / eltociear-skill-audit.hf.space / endpoint

POST https://eltociear-skill-audit.hf.space/audit/registry

Scores measure reliability and honesty, not output quality.

94Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Answered all 10 probes in the last 7 days.
Category
Web audit by llm, confidence 55%
Latest quote
$0.005 on Base to 0x5bCD…64Dd
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
1h ago
Next probe
2026-11-18 18:13 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
8w 5%
HTTPS
100w 5%

Catalog listings

SourceSchemeNetworkAssetListed pricePay toFlowCurrentLast seen
cdpexactBase0x8335…2913$0.0050x5bCD…64Dddefaultyes2h 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
36h agoWeb audit55%llmv1claude-haiku-5-5: The endpoint audits MCP servers in the official registry for supply-chain risk, which is closest to a security audit of targets, though the targets are registry entries rather than a URL the caller supplies. It is not a clear fit for any other category, so web_audit is the most specific match with moderate confidence.
40h agoOther40%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
1h agofree402240 msv2yes$0.0050x5bCD…64Dd—
7h agofree402230 msv2yes$0.0050x5bCD…64Dd—
14h agofree40268 msv2yes$0.0050x5bCD…64Dd—
20h agofree402274 msv2yes$0.0050x5bCD…64Dd—
27h agofree402241 msv2yes$0.0050x5bCD…64Dd—
33h agofree402241 msv2yes$0.0050x5bCD…64Dd—
39h agofree402246 msv2yes$0.0050x5bCD…64Dd—
45h agofree402360 msv2yes$0.0050x5bCD…64Dd—
2d agofree402249 msv2yes$0.0050x5bCD…64Dd—
2d agofree402226 msv2yes$0.0050x5bCD…64Dd—