LATIDIA · Ciberseguridad

MetaPermit: Control de acceso escalable y auditable para agentes de IA a través de metaatributos inferidos por LLM

arXiv: 2609.31039v1Tipo de anuncio: nuevo Resumen: El aumento de agentes autónomos de IA equipados con herramientas ha introducido importantes riesgos de seguridad, que van desde el uso indebido involuntario de herramientas hasta la manipulación contradictoria a través de INDI

La noticia

arXiv:2609.31039v1 Announce Type: new Abstract: The rise of autonomous AI agents equipped with tools has introduced significant security risks, ranging from unintended tool misuse to adversarial manipulation through Indirect Prompt Injection (IPI) attacks. In practice, deployed agent systems such as OpenAI Codex and Claude Code protect tool invocations through a combination of coarse-grained permission rules and LLM-based judgments about individual proposed actions. Both components, however, have important limitations: static policies must anticipate possible user intents and therefore do not scale to open-ended tasks, while LLM-driven authorization supports dynamic decisions but produces inconsistent outcomes and remains vulnerable to targeted IPI attacks. To provide scalable and more consistent authorization, we propose MetaPermit,