@sentinelhq/openclaw

Sentinel security hook for OpenClaw agents.

Install

npm install @sentinelhq/openclaw

Requires Node.js 20+

Usage

import { useSentinel } from '@sentinelhq/openclaw';

const guardedAgent = await useSentinel(agent, {
  policy: {
    spendingLimits: {
      maxPerTx: 1_000_000_000,   // 1 SOL
    },
  },
});

const result = await guardedAgent.executeAction('transfer', { to: '...', amount: 0.1 });

if (result.blocked) {
  console.log(result.blockedBy);  // 'prompt_guard' | 'execution_sandbox'
  console.log(result.reason);     // human-readable explanation
} else {
  console.log(result.result);     // action output
}

useSentinel returns a proxy that intercepts every executeAction() call through Sentinel's full three-layer pipeline (prompt guard, execution sandbox, memo attestation).

Configuration

The hook accepts the same configuration object as @sentinelhq/core — prompt guard mode, execution sandbox policy, and attestation settings are all supported.

Related Packages

| Package | Description | |----------|-------------| | @sentinelhq/core | Core SDK — Prompt Guard, Execution Sandbox, Memo Attestation | | @sentinelhq/cli | CLI — sentinel scan, simulate, attest, verify | | @sentinelhq/eliza | elizaOS plugin | | @sentinelhq/agent-kit | Solana Agent Kit middleware |

License

MIT