1
Breaking the Code: Security Assessment of AI Code Agents Through Systematic Jailbreaking Attacks
代码代理越狱风险远超纯文本，本研究系统性攻击揭示安全漏洞。
arXiv:2510.01359v2 Announce Type: replace-cross Abstract: Code-capable large language model (LLM) agents are embedded in software engineering workflow…