AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Maiat Trust Check

skill-moonpay-skills-maiat-trust-check · by moonpay

Check if an agent or token is trustworthy before transacting. Returns trust score and verdict from 29,000+ indexed agents on Base. Use before any swap, transfer, or agent interaction.

↗ Website ↗ Repository
— No reviews yet
0 installs
14 views
0.0% view→install

Install

$ agentstack add skill-moonpay-skills-maiat-trust-check

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ● Network access Used
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Maiat Trust Check? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

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=

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=" \
  --wallet  \
  --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

  1. User says: "Swap 100 USDC for TOKEN_X"
  2. Check trust: curl https://app.maiat.io/api/v1/trust?address=
  3. If avoid or unknown → warn user, do not proceed
  4. 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

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills