All projects matching “scoring”

Classify text an AI agent is about to read for prompt injection: verdict (safe, suspicious, malicious), score 0-100, findings with matched spans; decodes hidden Unicode tags, HTML comments, CSS-hidden text and base64 before scanning.

Order a full purchase test of any online store by an AI shopping agent: access, cookies, search, product page, cart, checkout, plus shipping, returns and guest-checkout facts with proof, UCP and machine readability. Same method as Neoavis public tests, private result with screenshots and a summary, score out of 100. Returns an order id and a result URL to poll; result usually within the hour.

Resolve a UK legal company name or registration number to a sourced Companies House profile. Returns company status, incorporation, SIC codes, registered office, filing due dates and overdue flags. Use for company research and CRM enrichment. Ambiguous names return candidates without settlement. Does not verify trading websites or provide credit scores.

Is this CVE weaponized? Returns enriched threat intelligence with exploit status, CVSS, EPSS, CISA KEV, ransomware mapping, and urgency score from 7 correlated sources.

Is this token safe to buy? Honeypot detection, rug-pull and scam check for any ERC-20 token contract -- flags can't-sell traps, hidden mints, malicious buy/sell taxes, unverified source, and holder concentration. GoPlus-powered token security scan with risk score 0-100. Not an audit.

Per-country sovereign economic / default-risk score (?country=<name or ISO3>)

GatiFlow topic signals: the latest collection's market and hiring signals on one topic, each with its sources, mention count and confidence score

dappgrade score — front-end integrity verdict for an onchain app, looked up by contract address. Inspects the app's public web front-end, not contract bytecode or admin control. Returns ok / caution / avoid / unknown with the coverage the verdict rests on.

Real-time crypto threat and risk intelligence for AI agents. Get up to 20 recent source-linked risk reports with risk scores, freshness, validation status and cached PG1 checks when available. Designed for automated triage and review. 0.01 USDC per snapshot on Base via x402; no API key or subscription required.

Cross-chain ERC-8004 trust score for one (chain, agent) pair — signed JSON with transparent component breakdown (value_avg / client_breadth / volume / recency), per-chain context, and methodology link. USDC pay-per-call on Base mainnet.

Return the full detected technology stack for a domain. Every technology is mapped to a category with a confidence score. Includes stack_sophistication, stack_gaps, and competing_vendors derived intelligence. Billed per domain profiled.

Use before paying an x402 endpoint you have not used before, when you cannot tell a working seller from a trap, a testnet address dressed as mainnet, or a listing whose price no longer matches its challenge. Returns a verdict — live, degraded, trap, testnet or dead — a 0-100 risk score, and the specific findings behind both, so an agent can decline a bad endpoint instead of learning about it by lo

Check one x402 endpoint: HTTP 402 status, parsed payment requirements (network, USDC price in USD, payTo, timeout), Bazaar metadata, issues with severity, latency, origin discovery docs, Bazaar listing with 30-day payers/calls, and a 0-100 score.

Send any x402 resource URL, get a trust verdict on the endpoint itself. Returns TRUSTED / CAUTION / AVOID with a 0-100 score from an observation-only live probe (never pays the target): payment terms, Bazaar discovery-schema quality, CDP Bazaar and PayAI catalog presence, plus a diff against the previous check. Use this when an agent is about to pay an unfamiliar x402 endpoint and needs to know it

Three composite AI readiness scores with history

Before your agent trusts, cites, or transacts with a U.S. bank: verify it is actually FDIC-insured, for $0.01, against the FDIC's own BankFind Suite records, synced daily. Look up by institution name (fuzzy, word-order-tolerant, confidence-scored), FDIC certificate number, or website domain. Returns insurance status, charter class, HQ city/state, and the FDIC cert; renamed and failed/inactive inst

Resolve a company name, website domain, registry number, LEI or VAT number to its official legal entity: registry, registry number, legal form, status, address, industry codes, size where published and LEI. Searches national registers (Norway, Finland, Czechia, Slovakia, France, UK, Latvia; Poland by KRS number) and GLEIF, scores the match and links every record to its source. Company-level only:

Fast, cheap spam-risk gate for one email: pass/warn/fail, a 0-100 score, and up to 3 flagged phrases. Use for a go/no-go before sending or for bulk screening of many drafts. No rewrites. For a full audit with reasons, subject-line risk, and rewritten copy, use analyze-email-deliverability. Content signals only; no inbox-placement guarantee.

Proprietary, daily-scored US residential real-estate deals for investors. Each on-market listing is graded (STRONG / MODERATE / FAIR) for flip, BRRRR, or buy-&-hold, with an estimated ARV from a live comp set, gross spread, margin %, cap rate / cash flow, days on market, comp count and the source URL. Filter by state, ZIP, city, price, beds, margin and ARV confidence. Coverage: FL, GA, NC, SC, AL,

Fishing conditions scored 0-100 from live NOAA data (NWS forecast and pressure trend, CO-OPS tides and water temperature), with moon phase, solunar periods and species intel.

Crypto wallet screening: OFAC SDN sanctions check (refreshed daily) and a 0-100 risk score, with balances, activity and transaction-graph checks for EVM wallets.

Fact-check one claim against live web sources (or URLs you supply). Returns a verdict (supported, refuted, mixed, insufficient), a confidence score and supporting or contradicting quotes that are checked verbatim against the fetched pages. Use it before an agent repeats a claim.

Single models are everywhere. This is the disagreement between them: per hour a median with a p15/p85 band, the full min/max spread, how many models still carry that hour, an agreement score, rain probability derived from pooled ensemble members rather than one deterministic run, a frost assessment, and the official DWD warnings in force for the point.

Voxight topic brief: a sourced intelligence brief on one AI, tech, market or crypto topic, written from the signals and narratives Voxight tracked over the last 30 days (key signals with their sources, what to watch, caveats, a confidence score). Use it when an agent needs a quick cited read of what is moving around a topic. Charged only when the brief is ready: the answer is 202 with an id to pol

Assess how trustworthy a domain is using authoritative live signals, not just its spelling. Fuses RDAP registration data (domain age — the single strongest phishing signal — plus registrar, expiry and registry status flags), DNS resolvability (A/AAAA), MX presence and DNSSEC into a 0-100 risk score with a verdict (low/medium/high) and the exact reasons. Pairs with `urltrust` (lexical) for a comple

Rerank documents against a query with BGE Reranker Base (@cf/baai/bge-reranker-base). POST query plus documents[]; returns relevance scores for search and RAG pipelines.

Prioritize up to 50 CVEs in one request using FIRST EPSS, CISA KEV, and known ransomware signals. Returns deterministic risk scores, urgency tiers, exploitation signals, vendor/product context, and remediation metadata as machine-readable JSON. Built for security automation and AI agents. No account or API key required. $0.01 per successful request via x402. Invalid input, no-signal results, and t

WalletTriage — real-time wallet risk check: dangerous ERC20 approvals cross-referenced with a live exploit threat feed. Returns risk_score (0-100), risk_level and actionable findings.

Fuzzy OFAC sanctions name screening: match a person, company, vessel or aircraft name against every SDN primary name and alias, returning scored potential matches (0-100, default threshold 85) with entity type, sanctions programs, DOB, nationality, aliases and OFAC links, plus the SDN list publication date. Screening aid, not legal advice. Free sample: https://sanctions-screen.mick8511.workers.dev

Analyze a Base wallet address for on-chain wallet due diligence, transaction-history research, and risk triage. Returns native balance, transaction and token-transfer counts, first and last activity, contract status, a heuristic activity score, and risk flags as JSON. Not identity verification or a guarantee that an address is safe.