arXiv cs.AI by Synapse Flow 編集部

Correct Code, Vulnerable Dependencies: A Large Scale Measurement Study of LLM-Specified Library Versions

概要

arXiv:2605.06279v1 Announce Type: cross Abstract: Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party library (TPL) imports annotated with specific version identifiers. These version choices can carry sec…

元記事を読む →

関連記事