Chat

AI Safety Guard

v18

Blockchain-Verified AI Safety Oracle

Every safety judgment is generated by on-chain AI inference, stored immutably on the Chromia blockchain, and protected against prompt injection with sentinel delimiters. Verdicts are cached for instant repeat checks.

Anti-InjectionDefault-SafeImmutable AuditCached VerdictsRate Limited

Test Safety Guard

Describe an action to evaluate. The AI will classify it as GREEN (safe), YELLOW (uncertain), or RED (dangerous).

API Endpoint (OpenClaw Compatible)

POST /api/judge

// Request body:

{
  "action": {
    "action": "Delete all files in /tmp",
    "context": "Running on production server"
  },
  "publicKey": "03d70bdae..."
}

// Response:

{
  "verdict": "red",
  "reason": "Dangerous file deletion",
  "judgmentId": "judge-api-...",
  "onChain": true,
  "cached": false
}