Work

LLM-Powered Secure Code Review Assistant for Student Projects: A Hybrid Approach Combining Static Analysis and Local Large Language Models

Year: 2026
Type: preprint
Abstract: This research presents an LLM-powered secure code review assistant designed to help student developers identify and understand potential security vulnerabilities in software projects. The proposed system combines static analysis tools, including Semgrep, Bandit, ESLint, SpotBugs, and Trivy, with a locally hosted Qwen large language model through Ollama. The platform supports ZIP file uploads and public GitHub repositories, coordinates security scanning, consolidates findings, and generates contextual explanations and potential remediation suggestions. It also provides a dashboard, scan history, and PDF and JSON reports. The paper describes the system architecture, workflow, implementation approach, security considerations, limitations, and proposed evaluation methodology. It distinguishes scanner-reported findings from AI-generated observations to avoid presenting unverified AI suggestions as confirmed vulnerabilities. Quantitative performance claims are not made because completed benchmark and user-study results are not reported.
Language: English
Open Access status: green
OpenAlex ID: W7234063817
Cites:
Cited by:
Related to: 10