Security & trust

Xynaptic Logistics Risk — current logistics disruptions affecting French/European flows: rail strikes (SNCF official data), sector press, + your specific route analysis. GET ?mode=rail (or POST a route description).

Scan a website for GDPR compliance indicators: cookie consent, privacy policy, tracking scripts, security headers. Returns score A-F.

Haworthia (Windows) — Reasoning-transparency framework for agents that need to expose internal process without dumping raw traces. Structured method: which decisions to surface, at what depth, in what format. For agents working with humans who need to audit reasoning, or agents proving reasoning to other agents (agent-to-agent trust chains). Translucent-leaf-tip principle: transparency is not exposure — it's window-shaped visibility at the point where light needs to enter.

First Wave — Gold rush history for understanding early-mover advantage and risk-taking.

The Barbershop Experience — Ritual grooming narrative for trust, transformation, and restoration through ceremony.

Husky — Storm — High-energy exploration companion for risk-taking and adventure motivation.

Siamese — Luna — Questioning companion for challenging assumptions and logic verification.

Pay-per-use EBT screening endpoint

Verify if a person meets a minimum age requirement based on their date of birth. Returns exact age, whether the threshold is met, and days until the threshold (if not met). Accounts for leap years.

Recall check straight from a VIN: the vehicle is decoded automatically, then matched against official safety recall campaigns — campaign number, component, what can fail, the risk, and the free remedy owed by the manufacturer. Fire-risk park-outside campaigns are flagged. One call, structured JSON.

Grade a domain's email-authentication and DNS-security posture from live DNS in one call: SPF, DMARC (policy + alignment), DKIM (for the supplied or common selectors), MTA-STS, TLS-RPT, DNSSEC, CAA, and BIMI. Pass domain (and optional dkimSelector). Returns an overall letter grade, a summary (spf/dmarcPolicy/dkim/mtaSts/dnssec/caa/bimi + spoofingProtected), and a per-mechanism block with the raw record, parsed tags, and specific issues (e.g. 'DMARC p=none — monitor only', 'SPF ~all soft-fail', 'no MTA-STS'). Sourced from live public DNS via DNS-over-HTTPS — an LLM cannot know a domain's current records. For deliverability/anti-spoofing audits, vendor security review, and phishing-resistance checks. DKIM is selector-based (selectors aren't enumerable), so 'not found' only means none of the checked selectors resolved.

Find live x402 endpoints worth paying, by capability: returns only endpoints Delx has live-probed, each with liveness score, last-observed timestamp, observed price, response-shape validity and Agents Hive ban-list status; every row cites its probe receipt, and ghost endpoints and dead quotes are filtered out before you spend. Limitation: observations, not endorsements — freshness is bounded by the last probe cycle, and absence from the directory means unprobed, not unsafe.

Audit an agent-facing service for machine usability. Actually calls the endpoints: MCP (Streamable HTTP initialize + tools/list, schema checks), A2A agent card, x402 payment challenge, llms.txt, OpenAPI, robots/agents metadata and endpoint health. Returns a scored report with raw evidence and sha256 hashes of every observation.

ERC-8004 Inspector agent lookup (identity + reputation) — per call

Is this x402 endpoint safe to pay? Vet an unknown seller BEFORE paying: pay/avoid verdict, 0-100 trust score, live 402 probe, scam flags (payTo hijack, bait-and-switch pricing, honeypot, wrong asset) and an on-chain check of the receiver on Base. Reads x402 v1 (body) AND v2 (PAYMENT-REQUIRED header) — body-only checkers call live v2 services dead. ?endpoint=url; omit for a trust-ranked catalog.

About page discovery audit fetches current public evidence from the supplied target and evaluates the documented criterion. It returns the observation, threshold, verdict, exact evidence source, limitations and a mode-specific action. The check is passive: no login attempt, payload injection, exploit, purchase, form submission or load test is performed.

Airdrop Sybil Score analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Selects and fills a small declared dialogue template using a caller-supplied seed, NPC name, intent, tone, and facts. It produces a reproducible writing prompt, not model-generated prose, lore verification, localization, or a complete conversation system.

Applies fixed coefficients to recency, session trend, playtime, support tickets, and recent purchases. It is an untrained scenario score, not an individualized prediction, psychological profile, causal model, or recommendation for manipulative retention.

Concentrated LP Range Optimizer analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Airdrop Eligibility Verifier analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Counts supplied outcomes, computes Pearson’s chi-square statistic, and estimates an upper-tail p-value with the Wilson-Hilferty normal approximation. It tests aggregate frequencies only; it cannot prove draw independence, seed fairness, code integrity, or manipulation, especially when expected counts are small.

Builder Inclusion Analyzer analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Collateral Correlation Risk analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Borrow-Curve Stress Test analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Cross-Chain Supply Reconciliation analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Freeze Event Monitor analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Recent earthquakes worldwide (USGS): magnitude, place, depth, tsunami flag — Genesis402 / UnyKorn Operator Network

Domain WHOIS/RDAP: registrar, created, expires, age, status, nameservers, DNSSEC — Genesis402 / UnyKorn Operator Network

TLS/SSL certificate check: issuer, expiry, days left, SANs, trust, protocol — Genesis402 / UnyKorn Operator Network