LATIDIA · Ciberseguridad

REALM: Identificación de activos de tareas mínimas para agentes de LLM

arXiv:2610.39155v1 Tipo de anuncio: nuevo Resumen: los agentes del modelo de lenguaje grande (LLM) a menudo reciben acceso a más archivos, cuentas y servicios de los que requiere una tarea. La inyección rápida convierte este exceso de acceso en un opportu

La noticia

arXiv:2610.39155v1 Announce Type: new Abstract: Large language model (LLM) agents often receive access to more files, accounts, and services than a task requires. Prompt injection turns this excess access into an opportunity to redirect execution toward unrelated resources. Applying least privilege therefore requires identifying the assets needed by a task, including assets whose identities emerge only during execution. We present REALM (Required Execution Assets Linked to a Mission), an approach to identifying and maintaining a task's required assets and their permitted uses. The approach represents required assets as Dependency Graph nodes, resolves prerequisite relationships, and admits newly discovered assets through source-scoped selection. It separates discovering an asset from authorizing its