collaborators

1 paper

cs.CR2026

Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States

Jianshuo Dong, Yiming Liu, Maosen Zhang +7

Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While many efforts have sought to address this t…