Evaluating Indirect Prompt Injection Defenses in Tool-Using LLM Agents: Security, Utility, and Replication

摘要: Large language model (LLM) agents that retrieve external content and use tools are vulnerable to indirect prompt injection, in which untrusted content

正文

Large language model (LLM) agents that retrieve external content and use tools are vulnerable to indirect prompt injection, in which untrusted content contains instructions intended to influence agent behavior. We evaluated four defenses and an undefended control across GPT-5.4, GPT-5.4-mini, ...

来源: Brave/mdpi.com