ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM Agents
Large language model (LLM) agents interact with external environments through tool invocation, but tool outputs can also expose them to indirect prompt injection (IPI) attacks. Existing defenses mainly rely on prompt hardening, content filtering, pre-generated plans, or permission constraints. These approaches often st...
Bing-Zheng Wang, Xiao-Yan Gu, Wen-Tao Wang et al.
· 1 citation