Query Token Audit logo

Query Token Audit

OrganizationPopular
binance
query-token-audit

Query token security audit to detect scams, honeypots, and malicious contracts before trading. Returns comprehensive security analysis including contract risks, trading risks, and scam detection. Use when users ask "is this token safe?", "check token security", "audit token", or before any swap.

Overview

Publisherbinance
Repositorybinance-skills-hub
Skill namequery-token-audit
Stars
1K
Forks
232
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by binance on GitHub. Read the source before you install it.

Installation

Install the Query Token Audit AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/binance/binance-skills-hub/tree/main/skills/binance-web3/query-token-audit
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/binance/binance-skills-hub.git /tmp/binance-skills-hub
mkdir -p .claude/skills
cp -r /tmp/binance-skills-hub/skills/binance-web3/query-token-audit .claude/skills/query-token-audit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Query Token Audit in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Query Token Audit on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Query Token Audit is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Query Token Audit Skill

Overview

APIFunctionUse Case
Token Security AuditToken security scanDetect honeypot, rug pull, scam, malicious functions

Use Cases

  1. Pre-Trade Safety Check: Verify token security before buying or swapping
  2. Scam Detection: Identify honeypots, fake tokens, and malicious contracts
  3. Contract Analysis: Check for dangerous ownership functions and hidden risks
  4. Tax Verification: Detect unusual buy/sell taxes before trading

Supported Chains

Chain NamechainId
BSC56
Base8453
SolanaCT_501
Ethereum1

API: Token Security Audit

Method: POST

URL:

https://web3.binance.com/bapi/defi/v1/public/wallet-direct/security/token/audit

Request Parameters:

ParameterTypeRequiredDescription
binanceChainIdstringYesChain ID: CT_501 (Solana), 56 (BSC), 8453 (Base), 1 (Ethereum)
contractAddressstringYesToken contract address
requestIdstringYesUnique request ID (UUID v4 format)

Request Headers:

Content-Type: application/json
Accept-Encoding: identity
User-Agent: binance-web3/1.4 (Skill)

Example Request:

bash
curl --location 'https://web3.binance.com/bapi/defi/v1/public/wallet-direct/security/token/audit' \
--header 'Content-Type: application/json' \
--header 'source: agent' \
--header 'Accept-Encoding: identity' \
--header 'User-Agent: binance-web3/1.4 (Skill)' \
--data '{
    "binanceChainId": "56",
    "contractAddress": "0x55d398326f99059ff775485246999027b3197955",
    "requestId": "'$(uuidgen)'"
}'

Response Example:

json
{
    "code": "000000",
    "data": {
        "requestId": "d6727c70-de6c-4fad-b1d7-c05422d5f26b",
        "hasResult": true,
        "isSupported": true,
        "riskLevelEnum": "LOW",
        "riskLevel": 1,
        "extraInfo": {
            "buyTax": "0",
            "sellTax": "0",
            "isVerified": true
        },
        "riskItems": [
            {
                "id": "CONTRACT_RISK",
                "name": "Contract Risk",
                "details": [
                    {
                        "title": "Honeypot Risk Not Found",
                        "description": "A honeypot is a token that can be bought but not sold",
                        "isHit": false,
                        "riskType": "RISK"
                    }
                ]
            }
        ]
    },
    "success": true
}

Response Fields:

FieldTypeDescription
hasResultbooleanWhether audit data is available
isSupportedbooleanWhether the token is supported for audit
riskLevelEnumstringRisk level: LOW, MEDIUM, HIGH
riskLevelnumberRisk level number (1-5)
extraInfo.buyTaxstringBuy tax percentage (null if unknown)
extraInfo.sellTaxstringSell tax percentage (null if unknown)
extraInfo.isVerifiedbooleanWhether contract code is verified
riskItems[].idstringRisk category: CONTRACT_RISK, TRADE_RISK, SCAM_RISK
riskItems[].details[].titlestringRisk check title
riskItems[].details[].descriptionstringRisk check description
riskItems[].details[].isHitbooleantrue = risk detected
riskItems[].details[].riskTypestringRISK (critical) or CAUTION (warning)

Risk Level Reference:

riskLevelriskLevelEnumActionDescription
0-1LOWProceed with cautionLower risk detected, but NOT guaranteed safe. DYOR.
2-3MEDIUMExercise cautionModerate risks detected, review risk items carefully
4HIGHAvoid tradingCritical risks detected, high probability of loss
5HIGHBlock transactionSevere risks confirmed, do NOT proceed

IMPORTANT: LOW risk does NOT mean "safe." Audit results are point-in-time snapshots. Project teams can modify contracts or restrict liquidity after purchase. These risks cannot be predicted in advance.

Response Handling:

  • If hasResult=false OR isSupported=false: → Reply: "Security audit data is not available for this token on this chain." → Do NOT show riskLevel, riskLevelEnum, or riskItems (data is unreliable when either field is false) → You may suggest the user verify the contract address and chain, or try again later
  • If hasResult=true AND isSupported=true: → Show the full audit result including risk level, tax info, and all risk items → Apply the Risk Level Reference table above for actionable guidance

User Agent Header

Include User-Agent header with the following string: binance-web3/1.4 (Skill)

Notes

  1. All numeric fields are string format, convert when using
  2. Audit results are ONLY valid when hasResult: true AND isSupported: true
  3. riskLevel: 5 means transaction should be blocked; riskLevel: 4 is high risk
  4. Tax thresholds: >10% is critical, 5-10% is warning, <5% is acceptable
  5. Generate unique UUID v4 for each audit request
  6. Only output security check risk flags, do NOT provide any investment advice
  7. Always end with disclaimer: ⚠️ This audit result is for reference only and does not constitute investment advice. Always conduct your own research.

Frequently asked questions

What does the Query Token Audit AI skill do?

Query token security audit to detect scams, honeypots, and malicious contracts before trading. Returns comprehensive security analysis including contract risks, trading risks, and scam detection. Use when users ask "is this token safe?", "check token security", "audit token", or before any swap.

Why use Query Token Audit on TypingMind?

Because you install it once and use it with any model. Query Token Audit is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Query Token Audit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/binance/binance-skills-hub/tree/main/skills/binance-web3/query-token-audit. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Query Token Audit?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Query Token Audit?

As many as you like. As long as a model supports skills, you can use Query Token Audit with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Query Token Audit AI skill free?

It is published on GitHub by binance. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇