alibaba/sec-code-bench

SecCodeBench is a benchmark suite focusing on evaluating the security of code generated by large language models (LLMs).

52
/ 100
Established

This project helps security researchers and AI model developers rigorously test the security of code generated by large language models (LLMs) and advanced coding AI agents. It takes in AI-generated code, runs comprehensive functional and security tests, and outputs a detailed security score and vulnerability report. The primary users are security experts focused on evaluating and improving the safety of AI-powered coding tools.

Use this if you need a robust, real-world benchmark to assess how securely your AI coding assistant or LLM generates and fixes code, especially against known vulnerabilities.

Not ideal if you are looking for a tool to secure your own manually written code or a simple static analysis tool for general software development.

AI-security-evaluation software-vulnerability-assessment LLM-code-generation secure-coding-benchmarking AI-agent-evaluation
No Package No Dependents
Maintenance 10 / 25
Adoption 9 / 25
Maturity 15 / 25
Community 18 / 25

How are scores calculated?

Stars

97

Forks

17

Language

Python

License

Apache-2.0

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/alibaba/sec-code-bench"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.