Open access
2026
Execution-Aware Stage-Wise Evaluation Framework for Indirect Prompt Injection in LLM-Based Email Agents
Indirect prompt injection (IPI) attacks have emerged as a critical security threat to large language model (LLM)-based email agents. However, existing evaluation benchmarks largely rely on simulated environments that cannot verify whether an attack will actually succeed in practice, often determining attack success sol...
Hyeonjin Jang, EunSeong Lee, Kyungbaek Kim et al.
· IEEE Access · 0 citations