# TrustAgent Deep Verify

> TrustAgent Deep Verify is a paid API for AI agents from trust-agent.io, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Analyzes a Base-chain contract or DeFi protocol address and returns a trust score, risk band, and pay/block recommendation.

## Facts

- Endpoint: GET https://trust-agent.io/v1/verify/deep
- 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/trustagent-deep-verify-b3deb488
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_OWTksZXJ8YNcYo2o32sU7

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 trustagent-deep-verify-b3deb488
```

Example prompt: Before my agent pays this contract, can you run a deep trust check on Base address 0x1234...abcd and tell me whether it's safe to proceed?

## When to prefer this

Choose this endpoint when an AI agent needs to make a go/no-go payment decision about a Base-chain contract, DeFi protocol, or agent wallet before executing a transaction. It is purpose-built for ERC-8004 payment safety gating and returns a structured recommendation (proceed/block) rather than raw on-chain data, making it ideal for autonomous agent workflows where a binary or banded safety signal is needed without manual review.

## Known failure modes

- Address not on Base chain — any chain other than 'base' is refused rather than answered from a different chain
- Address not found or undeployed — returns recommendation: insufficient_data with null trustScore
- Insufficient on-chain evidence — confidence near zero, recommendation: insufficient_data (treat as unknown, not risky)
- Invalid address format — likely 400 error
- Rate or payment failure — 402 Payment Required if x402 payment not completed

## How this service works

Should you approve this contract? Everything in quick, plus static analysis of the bytecode: privileged functions (mint, pause, blacklist, arbitrary withdrawal), proxy and upgradeability detection, dangerous opcodes, DeFi protocol classification and source-verification status.

## Output

Returns a JSON object with: trustScore (0-100, higher is safer, null if no rules could evaluate), riskBand (minimal | low | moderate | elevated | severe | unknown), recommendation (proceed | proceed_with_caution | hold | block | insufficient_data), confidence (0-1), per-rule scoring components, hard-cap overrides with reasons, contract bytecode analysis (opcodes, proxy kind, privileged functions, protocol class, safetyScore), and address-specific flags.

## 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"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [
      "address"
     ],
     "properties": {
      "type": {
       "type": "string",
       "description": "OPTIONAL. contract | defi_protocol."
      },
      "chain": {
       "type": "string",
       "description": "OPTIONAL. Only \"base\" is served; any other value is refused rather than answered from the wrong chain. Defaults to base."
      },
      "address": {
       "type": "string",
       "description": "REQUIRED. Contract address to analyse."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object",
     "properties": {
      "flags": {
       "description": "includes contract-specific findings"
      },
      "contract": {
       "description": "bytecode analysis: opcodes, proxy kind, privileged functions, interfaces, protocol class, safetyScore"
      },
      "riskBand": {
       "description": "minimal | low | moderate | elevated | severe | unknown"
      },
      "overrides": {
       "description": "hard caps applied after weighting, each with from/cap/reason"
      },
      "components": {
       "description": "per-rule scoring breakdown; the score is reconstructable from these plus overrides"
      },
      "confidence": {
       "description": "0-1, how much evidence backs the score"
      },
      "trustScore": {
       "description": "0-100, higher is safer; null when no rule could be evaluated"
      },
      "recommendation": {
       "description": "proceed | proceed_with_caution | hold | block | insufficient_data. insufficient_data means no judgment was possible — treat it as unknown, not as risky."
      }
     }
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "flags": "includes contract-specific findings",
  "contract": "bytecode analysis: opcodes, proxy kind, privileged functions, interfaces, protocol class, safetyScore",
  "riskBand": "minimal | low | moderate | elevated | severe | unknown",
  "overrides": "hard caps applied after weighting, each with from/cap/reason",
  "components": "per-rule scoring breakdown; the score is reconstructable from these plus overrides",
  "confidence": "0-1, how much evidence backs the score",
  "trustScore": "0-100, higher is safer; null when no rule could be evaluated",
  "recommendation": "proceed | proceed_with_caution | hold | block | insufficient_data. insufficient_data means no judgment was possible — treat it as unknown, not as risky."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/trustagent-deep-verify-b3deb488/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from trust-agent.io](https://www.zero.xyz/host/trust-agent.io/llms.txt)