Leaderboard / saferead.grindfree.net / endpoint
GET https://saferead.grindfree.net/v1/read
Scores measure reliability and honesty, not output quality.
- Listed only 0 days ago; new listings earn trust over 30 days.
- Answered all 4 probes in the last 7 days.
- 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
- HTTPS
- yes
- First listed
- 2026-11-16
- Last probe
- 4h ago
- Next probe
- 2026-11-17 22:41 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| cdp | exact | Base | 0x8335…2913 | $0.002 | 0xe4b5…721b | default | yes | 2h ago |
Listing changes
| When | Event | From | To |
|---|---|---|---|
| 7h ago | description_changed | Read clean: safe web page 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), comments, invisible Unicode, and agent-directed instructions — plus title, removed/flagged segments, an allow|warn|block verdict and fetch metadata. HTML, text, Markdown, JSON, PDF. GET ?url=<page URL> works too. | Read a web page as clean Markdown for AI (read clean). Use when your agent fetches a URL it did not write: returns LLM-ready Markdown with hidden HTML, comments, invisible Unicode and prompt injections removed or flagged, plus title, allow|warn|block verdict and fetch metadata. Honours robots.txt. Only successful reads are charged. Search intents: url to markdown, web page to markdown, read url. GET ?url=<page URL> works too. |
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.
| When | Category | Confidence | Method | Version | Evidence |
|---|---|---|---|---|---|
| 7h ago | Web audit | 90% | rules | v1 | rule web_audit matched "prompt injection" in description |
| 23h ago | Web audit | 90% | rules | v1 | rule web_audit matched "prompt injection" in description |
Probe history
| When | Kind | Status | Latency | x402 | Valid | Quoted | Pay to | Flags |
|---|---|---|---|---|---|---|---|---|
| 4h ago | free | 402 | 376 ms | v2 | yes | $0.002 | 0xe4b5…721b | — |
| 11h ago | free | 402 | 305 ms | v2 | yes | $0.002 | 0xe4b5…721b | — |
| 17h ago | free | 402 | 322 ms | v2 | yes | $0.002 | 0xe4b5…721b | — |
| 23h ago | free | 402 | 687 ms | v2 | yes | $0.002 | 0xe4b5…721b | — |