Many use cases for GenAI models involve models interacting with additional resources, from an internet-connected AGENT to a RETRIEVAL-AUGMENTED GENERATION (RAG) system depicted in Fig. 6. Because GenAI models combine the data and instruction channels, attackers can leverage the data channel to affect system operations by manipulating resources with which the system interacts. Thus, INDIRECT PROMPT INJECTION attacks are enabled by RESOURCE CONTROL that allows an attacker to indirectly (or remotely) inject system prompts without directly interacting with the application [146, 408].
