Logic layer Prompt Control Injection (LPCI): A Novel Security Vulnerability Class in Agentic Systems
This addresses a critical security problem for enterprises deploying LLM-based systems, though it is incremental as it builds on known prompt injection issues.
The paper identifies a new class of security vulnerabilities called Logic-layer Prompt Control Injection (LPCI) in agentic systems using LLMs, where encoded payloads in memory or tool outputs bypass filters and trigger unauthorized behavior across sessions.
The integration of large language models (LLMs) into enterprise systems has introduced a new class of covert security vulnerabilities, particularly within logic execution layers and persistent memory contexts. This paper introduces Logic-layer Prompt Control Injection (LPCI), a novel category of attacks that embeds encoded, delayed, and conditionally triggered payloads within memory, vector stores, or tool outputs. These payloads can bypass conventional input filters and trigger unauthorised behaviour across sessions.