LAAF: Logic-layer Automated Attack Framework A Systematic Red-Teaming Methodology for LPCI Vulnerabilities in Agentic Large Language Model Systems

Hammad Atta, Ken Huang, Kyriakos Rock Lambros +11

Agentic LLM systems equipped with persistent memory, RAG pipelines, and external tool connectors face a class of attacks - Logic-layer Prompt Control Injection (LPCI) - for which n…