jevbooks

← All projects

jev-risk-check-provider

caiovicentino/jev-risk-check-provider · Homepage

x402 risk-check provider with signed pre-payment verdicts for agents and wallets

Verification & Guardrails0.47Runner-up: Finance & TradingFunnel
Automated README summary

Automatically summarized from the README on 31 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

An x402 risk-check provider for agents and wallets: before paying or signing, it screens the counterparty against OFAC, phishing and drainer feeds, transaction simulation, drainer-kit fingerprints, and its own EIP-7702 kit watch, returning an ES256-signed attestation.

How it uses Jev

Jev reads the content the agent acted on (the request's context) for injected instructions, answering typed Noul/Choice/Score questions; its penalties and caps feed a code-controlled 0-100 score, and the verdict is issued as an ES256 attestation.

Primitives:choicescorenoul

Technique worth stealing

Treat the agent-facing content as untrusted state and let typed model questions only penalize or cap a deterministic score.

Try it

POST to https://x402check.xyz/v1/risk-check; an unpaid call returns 402 with payment options.

View on GitHub

Start using Jev: API key and your first request →

Model judgments from README excerpts

Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.

Models & evaluation dates

Inclusion gate
jev-1.14.0
Project signals
jev-1.14.0
Category
jev-1.14.0
Pattern tags
jev-1.14.0

Evidence

These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.

  • Jev is core to the projectFound in material0.92
  • Shows a System One patternFound in material0.79
  • Describes handling uncertaintynot found in the excerpt0.36
  • Reports measured numbersFound in material0.99
  • Is a runnable toolFound in material0.83
  • Top-10 learning shortlist signalnot found in the excerpt0.33
  • Is a replica of the modelnot found in the excerpt0.18
  • Solves a common problem (0–2)score on a 0–2 scale1.31 / 2
  • About JevFound in material0.98
Signals
Jev is core to the project0.92Shows a System One pattern0.79Describes handling uncertainty0.36Reports measured numbers0.99Is a runnable tool0.83Top-10 learning shortlist signal0.33Is a replica of the model0.1800.51Solves a common problem (0–2)1.31 / 2012

no-judgment band (0.40–0.60)

Design patterns
Funnel0.81Traffic light0.61Check-up0.42Questionnaire0.3100.51

no-judgment band (0.40–0.60)

The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 31 Oct 2026.