🦞 OpenClaw has 188k stars. It has no trust layer. We built it.

#openclaw #webdev #security #blockchain

Originally published at moltrust.ch/blog/openclaw-plugin.html

OpenClaw crossed 188,000 GitHub stars in roughly sixty days. Agents can now hold wallets, execute payments, install skills autonomously, and communicate with each other across platforms.

But there's a structural gap no amount of malware scanning fixes: OpenClaw has no agent identity system.

341 malicious skills found on ClawHub (Koi Security, Jan 2026)
13.4% of scanned ClawHub skills had critical security issues (Snyk)
135,000 exposed instances running with default configuration

Today we're releasing @moltrust/openclaw — W3C DID verification and reputation scoring as a native OpenClaw plugin.

Install

openclaw plugins install @moltrust/openclaw

Then restart your gateway.

What it does

Feature	Details
`moltrust_verify`	Verify any agent's W3C DID — returns VC details + trust score
`moltrust_trust_score`	0–100 reputation by DID or EVM wallet address
`/trust <did>`	Slash command in any OpenClaw channel
`/trustscore 0x...`	Free, no API key needed
`openclaw moltrust`	CLI subcommand
Self-verify on start	Your own DID checked at every gateway boot

Trust scores

🟢 80–100 (A) — trusted, safe to delegate
🟡 60–79 (B) — generally trustworthy
🟠 40–59 (C) — proceed with caution
🔴  0–39 (D) — high risk, do not delegate

Scores combine: on-chain transaction history, DID registration age, Verifiable Credential portfolio, sybil cluster analysis, funding trace.

Configuration

{
  "plugins": {
    "entries": {
      "moltrust": {
        "enabled": true,
        "config": {
          "apiKey": "mt_live_...",
          "minTrustScore": 40,
          "verifyOnStart": true,
          "agentDid": "did:moltrust:..."
        }
      }
    }
  }
}

Free tier available — wallet scoring requires no API key.

Why this matters: KYA

This plugin is the entry point for Know Your Agent (KYA) — the agent-economy equivalent of KYC, but cryptographic and decentralized.

OpenClaw agents interact autonomously. They pay for services, delegate tasks, install skills. The question "who is this agent and can I trust it?" is not philosophical — it's an operational requirement with financial consequences.

Email shipped without authentication — we got phishing. Social media shipped without identity verification — we got bot armies. Package managers shipped without code signing — we got supply chain attacks. OpenClaw is following the same trajectory.

MolTrust provides the infrastructure: W3C DIDs anchored on Base L2, Verifiable Credentials signed with Ed25519, and a reputation layer that aggregates signals into a single trust score.

DEV Community