LATIDIA · Ciberseguridad

PACE: Aplicación de la capacidad consciente de la procedencia para agentes de LLM que utilizan herramientas

arXiv: 2610.01349v1Tipo de anuncio: nuevo Resumen: Los agentes del modelo de lenguaje grande (LLM) que utilizan herramientas convierten el texto generado en efectos secundarios reales, por lo que los metadatos de herramientas envenenados, las páginas recuperadas, la memoria y las habilidades reutilizables pueden dirigir el

La noticia

arXiv:2610.01349v1 Announce Type: new Abstract: Tool-using large language model (LLM) agents turn generated text into real side effects, so poisoned tool metadata, retrieved pages, memory, and reusable skills can steer the next call. Vetting an artifact before admission does not settle this. A safe variant and a leaking variant can produce the same admission evidence, and a sound gate then cannot relax that site for either. We make that condition precise, which leaves the last boundary a deployment can still act on. We present Provenance-Aware Capability Enforcement (PACE), which mediates every tool call immediately before it executes. Path confinement proposes an executable cut of represented influence paths, while capability and