Skill

maiat-trust-check

Queries Maiat API for trust score and verdict on Base agents or tokens before swaps, transfers, or interactions. Analyzes behavior, completion rates, and on-chain history.

security

npx claudepluginhub moonpay/skills --plugin alchemy-skills

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Before interacting with any agent or token, check its trust score via Maiat. Returns a verdict (proceed/caution/avoid) based on behavioral analysis, completion rates, and on-chain history.

SKILL.md

Similar Skills

thoughtproof-reasoning-check

Verifies AI agent reasoning before high-value swaps, trades, or autonomous actions via adversarial multi-model critique (Claude, Grok, DeepSeek). Returns ALLOW, BLOCK, or UNCERTAIN with confidence score.

alchemy-skills

okx-security

231

Performs security scans for tokens (honeypots), EVM/Solana transactions pre-execution, DApps/URLs (phishing), signatures (EIP-712/personal_sign), and ERC20/Permit2 approvals.

4 files

onchainos-skills

erc-8004

Implements ERC-8004 for registering AI agents on EVM chains, managing on-chain identity, reputation, validation, and discovery with Agent0 TypeScript SDK.

8 files

tenequm-skills

Stats

Stars99

Forks18

Last CommitMar 21, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Maiat Trust Check

Goal

Before interacting with any agent or token, check its trust score via Maiat. Returns a verdict (proceed/caution/avoid) based on behavioral analysis, completion rates, and on-chain history.

Prerequisites

MoonPay CLI installed: npm install -g @moonpay/cli
A funded wallet on Base (for x402 paid endpoints): mp wallet create

Free API (no payment required)

curl https://app.maiat.io/api/v1/trust?address=<address>

x402 Paid API ($0.02 USDC on Base — no rate limit)

Using MoonPay CLI:

mp x402 request \
  --method GET \
  --url "https://app.maiat.io/api/x402/trust?address=<address>" \
  --wallet <wallet-name> \
  --chain base

Response

{
  "address": "0x...",
  "type": "agent",
  "trustScore": 85,
  "verdict": "proceed",
  "summary": "Reliable ACP agent — 42 jobs, 95% completion",
  "learnMore": "GET /api/v1/agent/0x..."
}

type is "agent", "token", or "unknown".

For full behavioral breakdown (completion rate, job history, etc.), use the paid /api/x402/reputation endpoint.

Decision logic

Score	Verdict	Action
80-100	`trusted` / `proceed`	Safe to interact
60-79	`caution`	Proceed with lower amounts
0-59	`avoid`	Do not interact
—	`unknown`	No data — treat as unverified

Example workflow

User says: "Swap 100 USDC for TOKEN_X"
Check trust: curl https://app.maiat.io/api/v1/trust?address=<TOKEN_X_ADDRESS>
If avoid or unknown → warn user, do not proceed
If proceed or trusted → execute the swap

Related skills

maiat-token-safety — Honeypot and rug pull detection
moonpay-swap-tokens — Execute the swap after trust check passes
moonpay-x402 — Pay for premium Maiat endpoints