Leaderboard / agents.crowdspark.me / endpoint
POST https://agents.crowdspark.me/v1/text/injection-check
Scores measure reliability and honesty, not output quality.
- Listed only 1 day ago; new listings earn trust over 30 days.
- Answered all 7 probes in the last 7 days.
- Category
- Web audit by rules, confidence 90%
- Latest quote
- $0.005 on Base to 0x0dEA…2eec
- 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 22:57 UTC
Score components
Catalog listings
| Source | Scheme | Network | Asset | Listed price | Pay to | Flow | Current | Last seen |
|---|---|---|---|---|---|---|---|---|
| payai | exact | Base | 0x8335…2913 | $0.005 | 0x0dEA…2eec | default | yes | 1h ago |
| cdp | exact | Base | 0x8335…2913 | $0.005 | 0x0dEA…2eec | default | yes | 2h ago |
Listing changes
| When | Event | From | To |
|---|---|---|---|
| 36h ago | description_changed | Detect prompt injection and jailbreak attempts in untrusted text such as scraped web pages, emails and tool output. JSON body {text} (max 50,000 chars). Rule-based detection of instruction override phrasing, role spoofing tags, data leak links and hidden Unicode in 6 languages. Returns verdict safe, suspicious or malicious, a 0-100 score and matched spans. Text is not stored. Free tier: 25 calls/day per IP with header X-Free-Call: 1 (or ?free=1). | Detect prompt injection and jailbreak attempts in untrusted text such as scraped web pages, emails and tool output. JSON body {text} (max 50,000 chars) or a batch {texts} or {items} (max 20). Optional source_type, sanitize and include_pii. Returns verdict safe, suspicious or malicious, severity, a 0-100 score and matched spans. Text is not stored. |
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 |
|---|---|---|---|---|---|
| 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 | 42 ms | v2 | yes | $0.005 | 0x0dEA…2eec | — |
| 11h ago | free | 402 | 52 ms | v2 | yes | $0.005 | 0x0dEA…2eec | — |
| 17h ago | free | 402 | 46 ms | v2 | yes | $0.005 | 0x0dEA…2eec | — |
| 23h ago | free | 402 | 384 ms | v2 | yes | $0.005 | 0x0dEA…2eec | — |
| 29h ago | free | 402 | 62 ms | v2 | yes | $0.005 | 0x0dEA…2eec | — |
| 35h ago | free | 402 | 230 ms | v2 | yes | $0.005 | 0x0dEA…2eec | — |
| 42h ago | free | 402 | 51 ms | v2 | yes | $0.005 | 0x0dEA…2eec | — |