> For the complete documentation index, see [llms.txt](https://docs.chaingpt.org/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.chaingpt.org/dev-docs-b2b-saas-api-and-sdk/chaingpt-claude-skill-and-plugin/products/smart-contract-auditor.md).

# Smart Contract Auditor

## Smart Contract Auditor

AI-powered vulnerability detection for Solidity smart contracts. Submit contract source code and receive a scored audit report identifying security issues, gas optimizations, and best-practice violations.

### Key Facts

|              |                                                    |
| ------------ | -------------------------------------------------- |
| **Endpoint** | `POST /chat/stream`                                |
| **Model**    | `smart_contract_auditor`                           |
| **Cost**     | 1 credit per request (2 with chat history enabled) |
| **SDK**      | `@chaingpt/smartcontractauditor`                   |
| **Output**   | Scored audit report with categorized findings      |

### Parameters

| Parameter     | Type   | Required | Description                                                                                                                      |
| ------------- | ------ | -------- | -------------------------------------------------------------------------------------------------------------------------------- |
| `model`       | string | Yes      | Must be `"smart_contract_auditor"`                                                                                               |
| `question`    | string | Yes      | The Solidity source code to audit, or a follow-up question about a previous audit                                                |
| `chatHistory` | string | No       | `"on"` or `"off"` (string, not boolean). Enables follow-up questions about findings. Doubles cost to 2 credits. Default: `"off"` |
| `sdkUniqueId` | string | No       | Unique session identifier for maintaining audit conversation context                                                             |

### Quick Start -- JavaScript

```bash
npm install @chaingpt/smartcontractauditor
```

```javascript
import { SmartContractAuditor } from "@chaingpt/smartcontractauditor";

const client = new SmartContractAuditor({
  apiKey: process.env.CHAINGPT_API_KEY,
});

const solidityCode = `
// SPDX-License-Identifier: MIT
pragma solidity ^0.8.19;

contract SimpleVault {
    mapping(address => uint256) public balances;

    function deposit() external payable {
        balances[msg.sender] += msg.value;
    }

    function withdraw(uint256 amount) external {
        require(balances[msg.sender] >= amount, "Insufficient balance");
        (bool success, ) = msg.sender.call{value: amount}("");
        require(success, "Transfer failed");
        balances[msg.sender] -= amount;
    }
}
`;

const audit = await client.createChatMessage({
  model: "smart_contract_auditor",
  question: solidityCode,
  chatHistory: "off",
});

console.log(audit.data.bot);
```

#### Follow-Up on Findings

```javascript
// Enable history to ask about specific findings
const audit = await client.createChatMessage({
  model: "smart_contract_auditor",
  question: solidityCode,
  chatHistory: "on",
  sdkUniqueId: "audit-session-001",
});

console.log(audit.data.bot);

// Ask for a fix recommendation
const followUp = await client.createChatMessage({
  model: "smart_contract_auditor",
  question: "Show me the corrected code with the reentrancy fix applied",
  chatHistory: "on",
  sdkUniqueId: "audit-session-001",
});

console.log(followUp.data.bot);
```

### Tips

* The Auditor detects common vulnerabilities including reentrancy, integer overflow, access control issues, and gas inefficiencies.
* Pair with the Smart Contract Generator for a generate-then-audit pipeline.
* Use chat history to drill into specific findings and request corrected code, but note the doubled credit cost.
* For the example above, the Auditor will flag the classic reentrancy vulnerability in the `withdraw` function (state update after external call).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.chaingpt.org/dev-docs-b2b-saas-api-and-sdk/chaingpt-claude-skill-and-plugin/products/smart-contract-auditor.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.