AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software

TL;DR

This large-scale empirical study investigates the prevalence, security implications, and ecosystem impact of AI-generated code in modern software, revealing structured adoption patterns and security risks associated with AI in code development.

Contribution

The paper introduces a high-precision detection pipeline and a comprehensive benchmark to distinguish AI-generated code from human-written code in real-world repositories and vulnerability data.

Findings

AI-generated code constitutes a significant portion of new code, mainly in boilerplate and non-critical areas.

Certain security weakness types are overrepresented in AI-generated code, indicating potential security risks.

AI accelerates code changes but can introduce persistent vulnerabilities when human review is shallow.

Abstract

Large language models (LLMs) for code generation are becoming integral to modern software development, but their real-world prevalence and security impact remain poorly understood. We present the first large-scale empirical study of AI-generated code (AIGCode) in the wild. We build a high-precision detection pipeline and a representative benchmark to distinguish AIGCode from human-written code, and apply them to (i) development commits from the top 1,000 GitHub repositories (2022-2025) and (ii) 7,000+ recent CVE-linked code changes. This lets us label commits, files, and functions along a human/AI axis and trace how AIGCode moves through projects and vulnerability life cycles. Our measurements show three ecological patterns. First, AIGCode is already a substantial fraction of new code, but adoption is structured: AI concentrates in glue code, tests, refactoring, documentation, and other boilerplate, while core logic and security-critical configurations remain mostly human-written. Second, adoption has security consequences: some CWE families are overrepresented in AI-tagged code, and near-identical insecure templates recur across unrelated projects, suggesting "AI-induced vulnerabilities" propagated by shared models rather than shared maintainers. Third, in human-AI edit chains, AI introduces high-throughput changes while humans act as security gatekeepers; when review is shallow, AI-introduced defects persist longer, remain exposed on network-accessible surfaces, and spread to more files and repositories. We will open-source the complete dataset and release analysis artifacts and fine-grained documentation of our methodology and findings.