nursca/contract-auditor — explained in plain English
Analysis updated 2026-05-18
Paste a Solidity contract before deploying it to catch common vulnerabilities early.
Get a quick risk score to prioritize which contracts need a deeper manual audit.
Spot payment or refund logic errors that plain rule based scanners tend to miss.
| nursca/contract-auditor | 100/rutgers-pbl-dining-2015 | a15n/a15n_old | |
|---|---|---|---|
| Stars | 0 | — | — |
| Language | HTML | HTML | HTML |
| Last pushed | — | 2015-12-01 | 2016-06-18 |
| Maintenance | — | Dormant | Dormant |
| Setup difficulty | moderate | easy | easy |
| Complexity | 3/5 | 1/5 | 1/5 |
| Audience | developer | general | general |
Figures from each repo's GitHub metadata at analysis time.
Requires Node.js 18+ and a paid Anthropic API key to run the AI analysis locally.
Contract Auditor is a tool that checks Solidity smart contracts for security problems. Solidity is the programming language used to write smart contracts, the code that runs on blockchains like Ethereum. A user pastes their contract code into the app and within about fifteen seconds gets back a report listing any vulnerabilities found, ranked by how serious they are. The tool combines two different checking methods. First, a set of seven fixed rules looks for well known problems such as reentrancy attacks, unchecked external calls, missing access control, and unbounded loops. Second, an AI model reviews the same code looking for logic mistakes in payment or refund calculations that the fixed rules would not catch on their own. Both checks run at the same time rather than one after another, which keeps the wait short. If the AI check fails or takes too long, the app still shows the results from the fixed rule checks instead of failing outright. Findings are sorted from critical down to informational, and the report includes an overall risk score out of 100. When both the fixed rules and the AI model flag the same issue, it is marked as a higher confidence finding. The app does not save or log the contracts people submit, so nothing pasted into it is stored afterward. The project is built with Next.js, TypeScript, and Tailwind for the interface, and it calls the Claude API to power the AI portion of the analysis. It is meant to run as a web app deployed on Vercel, and setup requires Node.js and an Anthropic API key. Right now it only checks one file at a time, has no accounts or saved history, and was built as an entry for a hackathon called the Web3LadiesBuildWithAI Ship It Challenge. The listed next steps include more thorough analysis, checking whole GitHub repos with multiple files, and exporting reports as PDFs.
An AI-assisted scanner that reads pasted Solidity code and returns a ranked report of security vulnerabilities in seconds.
Mainly HTML. The stack also includes Next.js, TypeScript, Tailwind.
No license information is stated in the README.
Setup difficulty is rated moderate, with roughly 30min to a first successful run.
Mainly developer.
This repo across BitVibe Labs
double-check against the repo, no cap.