Paywary

Leaderboard / saferead.grindfree.net / endpoint

POST https://saferead.grindfree.net/v1/read

Scores measure reliability and honesty, not output quality.

92Payconfidence: medium
  • Listed only 2 days ago; new listings earn trust over 30 days.
  • Quoted a price different from the listed price on 1 of 5 comparable probes.
Category
Web audit by rules, confidence 90%
Latest quote
$0.002 on Base to 0xe4b5…721b
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
2h ago
Next probe
2026-11-18 18:20 UTC

Score components

Uptime, 7 days
100w 15%
Uptime, 30 days
100w 15%
Valid x402 challenge
100w 15%
Price honesty
90w 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$0.0020xe4b5…721bdefaultyes3h ago

Listing changes

WhenEventFromTo
9h agodescription_changedSafe web reader for AI agents: fetches a URL (SSRF-guarded) and returns clean Markdown or text with hidden content and prompt injections removed or flagged — hidden HTML (display:none, font-size:0, off-screen, aria-hidden), comments, invisible Unicode, and agent-directed instructions — plus title, removed/flagged segments with reasons, an allow|warn|block verdict and fetch metadata. HTML, plain text, Markdown, JSON and PDF.Read a web page as clean Markdown for AI. Use when your agent fetches a URL it did not write: hidden text, comments, invisible Unicode and prompt injections are removed (see removed_count) plus a verdict. Public benchmark: removed 129/129 injections, 0/23 false positives, 72% on an untuned hold-out; Jina Reader 26%, html2text 11%. Honours robots.txt; only successful reads charged. Search intents: url to markdown.
9h agoreappearedfalsetrue
40h agodisappeared——
2d agoprice_changed30002000

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
9h agoWeb audit90%rulesv1rule web_audit matched "prompt injection" in description
37h agoWeb scrape35%llmv1claude-haiku-5-5: The host name and resource path '/v1/read' suggest it fetches and reads a web page for the caller, which points to web_scrape. However, there is no service name, tags, description, or example input, so the classification rests only on the URL and is low confidence.
40h agoOther20%rulesv1rule none matched "" in none

Probe history

WhenKindStatusLatencyx402ValidQuotedPay toFlags
2h agofree402296 msv2yes$0.0020xe4b5…721b—
8h agofree402509 msv2yes$0.0020xe4b5…721b—
14h agofree402501 msv2yes$0.0020xe4b5…721b—
21h agofree402343 msv2yes$0.0020xe4b5…721b—
27h agofree402312 msv2yes$0.0020xe4b5…721b—
33h agofree402343 msv2yes$0.0020xe4b5…721b—
40h agofree402448 msv2yes$0.0020xe4b5…721b—
46h agofree402328 msv2yes$0.0020xe4b5…721b—
2d agofree402296 msv2yes$0.0020xe4b5…721b—
2d agofree402333 msv2yes$0.0020xe4b5…721bprice_below_listingprice_mismatch