LATIDIA · Ciberseguridad

Comprensión y mitigación de ataques entre sesiones a través de artefactos persistentes en la composición de habilidades de agentes

arXiv:2610.13227v1 Announce Type: new Resumen: Las habilidades de los agentes amplían las capacidades de los agentes de IA agrupando instrucciones, código y recursos en paquetes reutilizables. Durante la ejecución de la habilidad, los agentes pueden producir o modificar

La noticia

arXiv:2610.13227v1 Announce Type: new Abstract: Agent skills extend the capabilities of AI agents by bundling instructions, code, and resources into reusable packages. During skill execution, agents may produce or modify artifacts, such as files, configurations, and cached data, that are reused by other skills in later sessions. Since these artifacts can persist across sessions and later be accessed by other skills, they introduce a new attack surface that can be exploited to influence subsequent executions. However, the security risks arising from such cross-session skill interactions remain largely unexplored. In this work, we investigate cross-session composition attacks in skill-based AI agents and develop a runtime defense against them. Specifically, we characterize