The paper introduces SUSVIBES, a benchmark of 186 real‑world software engineering tasks where human programmers have committed vulnerable code. It evaluates 12 popular coding‑agent settings on these tasks and finds that all agents perform poorly in terms of security, with only 11.8% of solutions from SWE‑Agent with Claude 4 Sonnet being secure despite 57% being functionally correct. Attempts to mitigate security issues by adding vulnerability hints to the prompts do not improve results.
By Songwen Zhao, Danqing Wang, Kexun Zhang, Jiaxuan Luo, Zhuo Li, Lei Li
arXiv:2607. 23088v1 Announce Type: cross Abstract: Large Language Models (LLMs) are widely used for code generation, yet their security behavior in realistic development workflows remains underexplored.
By Lixun Ma, Ruolong Ma, Bei Wang, Feng Wei, Zhenguang Liu, Lorenzo Cavallaro, Wentao Chen
arXiv:2610.14766v1 Announce Type: cross
Abstract: AI coding agents now write much of the code that ships, yet whether that code is secure remains unclear. We introduce the Last Secure Code Benchmark,...
By Tianyi Wu, Chao Ge, Peng Chen, Fengji Zhang, Yongxing Wu, Yuchong Xie, Jian Li, Chaoyuan Peng, Kaikai Zhang, Dong Huang, Mingzhe Du, Yukai Huang, Jiaheng Zhang, Terry Yue Zhuo, See-Kiong Ng
arXiv:2607. 23710v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly integrated into software development workflows, yet their ability to autonomously generate secure authentication code remains uncertain.
By Ishpuneet Singh, Shreyas Mahajan, Gurjot Singh, Maninder Singh
SecureVibe is a training recipe designed to enhance the security of vibe coding by explicitly targeting planning and testing for code security. It combines supervised fine‑tuning on a security suite with post‑training methods (SECUREVIBE_rl and SECUREVIBE_hg) that use verifiable execution feedback and hint‑based self‑supervision. The approach outperforms baselines on multiple security coding benchmarks, improving security pass@1 by up to 6.9 points on BaxBench and 11.5 points on SusVibes, while also boosting functionality pass@1 on both security and generic coding tasks.
By Danqing Wang, Baolin Peng, Zhepei Wei, Isadora White, Wenlin Yao, Hao Cheng, Qianhui Wu, Minseon Kim, Xingdi Yuan, Lei Li, Jianfeng Gao
arXiv:2601. 19138v2 Announce Type: replace-cross Abstract: Secure code review is critical during pre-integration, where Atlassian developers rely on lightweight analysis tools, while deep security assessment is deferred to later stages, delaying feedback and increasing remediation costs.
By Wachiraphan Charoenwet, Kla Tantithamthavorn, Patanamon Thongtanunam, Hong Yi Lin, Minwoo Jeong, Ming Wu
arXiv:2606. 30587v1 Announce Type: cross Abstract: Researchers and practitioners increasingly apply Large Language Models (LLMs) for automated vulnerability detection.
By Asif Shahriar, Hongyu Cai, Hadjer Benkraouda, Gang Wang, Z. Berkay Celik
Coding agents are increasingly used for software engineering tasks, including bootstrapping projects from third-party repositories whose integrity cannot be assumed. Prior work on repository poisoning...
The paper introduces NameTrap, a source‑code poisoning attack that renames identifiers in third‑party Python files to steer AI coding agents toward specific Common Weakness Enumeration (CWE) vulnerabilities. By iteratively aligning variable names with CWE‑specific conventions, the attack achieves success rates ranging from 22.5% to 75.0% across six agents and four vulnerability categories, outperforming random and neutral renaming strategies. The poisoned files contain no explicit instructions or vulnerable statements, and existing AI‑based and static security analyzers fail to detect the induced weaknesses.
By Chieh-Yuan Chang, Guan-Wei Chen, Chia-Yi Hsu, Chih Yang, Chia-Mu Yu, Chun-Ying Huang
arXiv:2606. 15762v1 Announce Type: cross Abstract: We ran 300 repeated vulnerability-finding scans to measure how repeatable agentic large language model (LLM) security review is on the same JavaScript code, prompt, and benchmark harness.
By Liran Tal, Johannes Kloos, Arsenii Rudich, Stephen Thoemmes, Manoj Nair
arXiv:2601. 21233v2 Announce Type: replace Abstract: Autonomous code agents built on large language models are reshaping software and AI development through tool use, long-horizon reasoning, and self-directed interaction.
By Xiang Zheng, Yutao Wu, Hanxun Huang, Yige Li, Xingjun Ma, Bo Li, Yu-Gang Jiang, Cong Wang
The paper introduces the Static‑Pass Dynamic‑Fail (SPDF) phenomenon, showing that static analysis can miss vulnerabilities that are exploitable at runtime. Using a three‑stage pipeline—static scanning, LLM‑driven CWE reasoning, and autonomous exploit verification—it evaluated 1,355 Python samples and found that 14.53% of samples that passed static checks were actually exploitable. The study highlights that static‑analysis success and runtime security are distinct assurance layers, especially for AI‑generated and security‑sensitive code.
By Jessica Pourleyli, Maitreyee Das Urmi, Glaucia Melo