# DCL Trust Oracle — Baseline AI Agent Safety Evaluator

> DCL Trust Oracle — Baseline AI Agent Safety Evaluator is a paid API for AI agents from bazaar.fronesislabs.com, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Performs baseline safety screening of agent outputs to detect harmful, unsafe, or policy-violating content before the agent acts on them.

## Facts

- Endpoint: GET https://bazaar.fronesislabs.com/evaluate/safety
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/dcl-trust-oracle-baseline-ai-agent-safety-evaluator-16440da2
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_U6wdT57YFzKU0Hi5Ue--m

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability dcl-trust-oracle-baseline-ai-agent-safety-evaluator-16440da2
```

Example prompt: Run a baseline safety check on this output I'm about to send — use the DCL Trust Oracle to get a verdict and confidence score so I know whether it's safe to proceed.

## When to prefer this

Choose this endpoint for fast, low-cost ($0.01 USDC) baseline safety screening of routine agent outputs where speed matters and on-chain auditability (tx_hash, chain_index) is desired. Prefer it over heavier evaluation tiers when the action is reversible and confidence thresholds don't need to be extremely high. It is especially suitable for high-volume agent pipelines that need lightweight pre-action safety gates without blocking latency.

## Known failure modes

- Missing required 'input' body field returns validation error
- Invalid HTTP method enum value (not GET/HEAD/DELETE) causes schema rejection
- Service unavailability or payment failure (x402) prevents evaluation
- Empty or malformed agent output may result in low-confidence verdicts
- Network timeout if agent pipeline is under heavy load

## How this service works

Baseline safety screening for harmful, unsafe, or policy-violating agent outputs.

## Output

Returns a structured safety evaluation including: a string verdict (e.g. safe/unsafe), a numerical confidence score, a human-readable reason for the verdict, an input hash for auditability, a blockchain transaction hash and chain index for on-chain logging, a drift score and drift mode indicating behavioral deviation, and a policy version identifier and timestamp.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET",
      "HEAD",
      "DELETE"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "properties": {}
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "required": [
      "verdict",
      "confidence",
      "reason",
      "tx_hash",
      "chain_index"
     ],
     "properties": {
      "reason": {
       "type": "string"
      },
      "tx_hash": {
       "type": "string"
      },
      "verdict": {
       "type": "string"
      },
      "timestamp": {
       "type": "number"
      },
      "confidence": {
       "type": "number"
      },
      "drift_mode": {
       "type": "string"
      },
      "input_hash": {
       "type": "string"
      },
      "chain_index": {
       "type": "integer"
      },
      "drift_score": {
       "type": "number"
      },
      "policy_version": {
       "type": "string"
      }
     }
    }
   }
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/dcl-trust-oracle-baseline-ai-agent-safety-evaluator-16440da2/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from bazaar.fronesislabs.com](https://www.zero.xyz/host/bazaar.fronesislabs.com/llms.txt)