LATIDIA · Ciberseguridad

Habilidades de encadenamiento para secuestrar agentes de LLM

arXiv: 2610.01564v1Tipo de anuncio: nuevo Resumen: los agentes de LLM utilizan habilidades para mejorar el rendimiento en tareas especializadas. Para completar una solicitud de usuario, un agente puede invocar varias habilidades en secuencia, lo que permite que la información producida

La noticia

arXiv:2610.01564v1 Announce Type: new Abstract: LLM agents use skills to improve performance on specialized tasks. To complete a user request, an agent may invoke several skills in sequence, allowing information produced under one skill to guide the next. Because skills may come from open-source repositories, this handoff can also carry attacker-controlled claims into later decisions. In this paper, we introduce APEX, which constructs and refines adversarial skill chains tailored to a user task and an attacker-selected action. The key insight is that an agent-written record of genuine task progress can carry a false claim of user approval across skills: an upstream skill induces the agent to create the record, and