arXivXiaodong Wu, Yu Shi, Qi Li, Zhimin Zhao, Xiangman Li, Bram Adams, Ahmed E. Hassan, Jianbing NiWed, Aug 26, 2026, 6:19 AM PDT
score 17.1
AI coding agents can be tricked into spreading hidden malware
Original: EVOMAL: Self-Poisoning in Self-Evolving Coding Agents
Source: arxiv.org ↗
Writing ELI5 summary…