arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.01052cs.CRcs.AI
收藏

VibeGuard:面向AI生成代码的安全闸门框架

VibeGuard: A Security Gate Framework for AI-Generated Code

Kennesaw State University(肯尼索州立大学)

Ying Xie

AI总结:

本文提出VibeGuard,针对AI生成代码中的五个盲点提供预发布安全检查,通过实验验证其在八个合成项目中的高召回率和精度,为依赖AI生成代码的团队提供多层次防御策略。

摘要:

本文提出VibeGuard,针对AI生成代码中的五个盲点提供预发布安全检查,通过实验验证其在八个合成项目中的高召回率和精度,为依赖AI生成代码的团队提供多层次防御策略。

英文摘要:

"Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption in production settings. On March 31, 2026, Anthropic's Claude Code CLI shipped a 59.8 MB source map file in its npm package, exposing roughly 512,000 lines of proprietary TypeScript. The tool had itself been largely vibe-coded, and the leak traced to a misconfigured packaging rule rather than a logic bug. Existing static-analysis and secret-scanning tools did not cover this failure mode, pointing to a gap between the vulnerabilities AI tends to introduce and the vulnerabilities current tooling is built to find. We present VibeGuard, a pre-publish security gate that targets five such blind spots: artifact hygiene, packaging-configuration drift, source-map exposure, hardcoded secrets, and supply-chain risk. In controlled experiments on eight synthetic projects (seven vulnerable, one clean control), VibeGuard achieved 100% recall, 89.47% precision (F1 = 94.44%), and correct pass/fail gate decisions on all eight projects across three policy levels. We discuss how these results inform a defense-in-depth workflow for teams that rely on AI code generation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑