# TrollBridge /shield — One-Call Token Safety Screen

> TrollBridge /shield — One-Call Token Safety Screen is a paid API for AI agents from mini-tollbooth.onrender.com, paid per call via x402, $0.25/call, status unknown (last checked 2026-10-11).

Runs a comprehensive don't-get-rugged battery (honeypot, rug-pull, contract safety, and optional wallet approvals) on a token contract address and returns a single GO/CAUTION/NO-GO verdict with a 0-100 safety score.

## Facts

- Endpoint: GET https://mini-tollbooth.onrender.com/shield?utm_source=zero.xyz
- Price: $0.25/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-11
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/trollbridge-shield-one-call-token-safety-screen-34e4045f
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_vzzHi8EgwDRtLneYdIE3h

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 trollbridge-shield-one-call-token-safety-screen-34e4045f
```

Example prompt: Before you touch it, run a full shield screen on the token at 0x1234abcd... on Base — I need a GO/CAUTION/NO-GO verdict and safety score so I know if it's safe to swap.

## When to prefer this

Use /shield when you need a single, all-in-one safety verdict before an agent touches a token — it bundles honeypot detection, rug-pull scoring, and contract safety checks into one $0.25 call. Prefer this over calling individual checks (/honeypot-check, /rug-score, /contract-check separately) when speed and simplicity matter more than granular per-check cost control. Ideal for AI agents about to execute a swap, approve a contract, or interact with an unfamiliar token and needing a fast, actionable GO/CAUTION/NO-GO decision.

## Known failure modes

- Missing required 'address' query param returns an error
- Invalid or non-checksummed contract address may return an error or degraded result
- Chain not in ['base','ethereum'] returns a validation error
- Contract not deployed on specified chain may return empty or inconclusive findings
- Service unavailable (hosted on Render free tier, may cold-start or time out)
- Payment failure (requires $0.25 USDC via x402 protocol) blocks the call

## How this service works

The insurance booth for AI agents, with Mini's Agent Supply Store on the side of the road. One hundred checkpoints: pre-transaction safety lanes (honeypot, approval-risk, rug-score, receipt-check, tx-dryrun, permit-scan, airdrop-verdict, deployer-history, wallet-watch, secret-scan at $0.02 USDC per call; the protection tier — /contract-check, /approval-screen, /tx-plain-english, /honeypot-check, /tx-simulate, /redteam, /skill-scan, /verdict, /egress-audit, /tool-gate, /airlock, /repo-scan, /prove, /task-scope — at $0.10; the one-call /shield don't-get-rugged screen at $0.25; the full /preflight bundle at $0.05), bounty intel (bounties, fresh, verdicts, deadlines, sweepstakes, opportunities) at $0.02 USDC per call, trader intel (/prices and /quant at $0.02; /enrich and /token-check at $0.05; /contract-check and /honeypot-check at $0.10; /sec-facts at $0.05), market intel (/markets and /search at $0.05; /grants at $0.02), DeFi intel (/yields and /new-pairs at $0.05; /gas and /defi at $0.02), AI intel (/models at $0.02), agent-ops intel (/prompt-cost, /model-picks, /rpc-speed, /terms-tldr, /scrape, /gigs, /retry-verify, /idempotency, /verify-independent at $0.02; /site-watch, /wallet-check, /code-run, /regulatory-pack, /sage, /cron-watch, /caveat-check, /tripwire, /escrow, /trust, /bridge-fees, /dao-votes, /dev-activity, /dex-arb, /dydx-perps, /funding-rates, /gas-predict, /hack-tracker, /long-short-ratio, /lp-yields, /mev-scan, /open-interest, /perp-basis, /polymarket-odds, /rwa-watch, /sentiment, /stablecoin-flows, /tokenomics, /top-movers, /whale-watch, and /yield-stable at $0.05; /approval-screen, /tx-plain-english, /tx-simulate, and /task-scope at $0.10; /scam-scan deep scan at $5.00 or 30-day subscription at $30.00), supply store (/road-pack combo meal at $0.05; curated datasets, the /audit-prep pre-audit review, and the /prove-state symbolic-execution run at $1.00; the /audit AI-agent audit at $25.00). Every lane answers before money moves — heuristic verdicts, not audits. Don't get rugged.

## Output

A JSON object containing: a GO/CAUTION/NO-GO verdict, a 0-100 safety score, a human-readable summary and reason, an array of findings (each with check name, signal, summary, and risk_score), an evidence array (each with check, claim, detail, source, severity, and a block explorer link), a list of checks_run, and a disclaimer that this is a heuristic screen not a full audit.

## 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": {
      "chain": {
       "enum": [
        "base",
        "ethereum"
       ],
       "type": "string",
       "description": "Which chain (default base)."
      },
      "wallet": {
       "type": "string",
       "description": "Optional wallet address (0x…) to include the wallet approval screen. Omit to skip it."
      },
      "address": {
       "type": "string",
       "description": "Token contract address to shield-screen before touching (0x… on Base or Ethereum)."
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "lane": "/shield",
  "chain": "base",
  "score": 92,
  "reason": "…",
  "wallet": null,
  "address": "0x...",
  "summary": "…",
  "verdict": "GO",
  "warning": "NOT AN AUDIT — heuristic screen…",
  "evidence": [
   {
    "link": "https://basescan.org/address/0x...#code",
    "check": "honeypot",
    "claim": "Contract source is NOT verified",
    "detail": "…",
    "source": "Blockscout contract verification status",
    "severity": "high"
   }
  ],
  "findings": [
   {
    "check": "honeypot",
    "signal": "looks-ok",
    "summary": "…",
    "risk_score": 5
   }
  ],
  "checks_run": [
   "honeypot",
   "rug-score",
   "contract-check"
  ],
  "description": "NOT AN AUDIT — the one-call don't-get-rugged screen: the full protection battery (honeypot, rug-pull, contract safety, plus wallet approvals with ?wallet=) in a single $0.25 call. One verdict — GO, CAUTION, or NO-GO — with a 0-100 safety score. For agents about to touch a token."
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/trollbridge-shield-one-call-token-safety-screen-34e4045f/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from mini-tollbooth.onrender.com](https://www.zero.xyz/host/mini-tollbooth.onrender.com/llms.txt)