LATIDIA · Ciberseguridad

Pérdidas ilimitadas, entradas no verificadas: medición de las salvaguardas de los agentes de negociación de opciones de LLM

arXiv: 2610.24289v1Tipo de anuncio: nuevo Resumen: los agentes del modelo de lenguaje grande (LLM) ahora realizan pedidos de opciones a corredores minoristas, y los desarrolladores publican agentes de opciones de código abierto más rápido de lo que nadie los ha examinado. Anterior

La noticia

arXiv:2610.24289v1 Announce Type: new Abstract: Large language model (LLM) agents now place options orders at retail brokers, and developers publish open-source options agents faster than anyone has examined them. Prior security work on trading agents scored academic equities designs by whether an attacker can flip a buy-or-sell decision. We present the first measurement of the options agents that brokers and developers ship, scored by the safeguards they enforce and by the worst loss their documented order paths can reach. We screened 765 GitHub repositories, broker documentation, and the research literature and found 215 eligible repositories and 8 broker-native agent interfaces. We then scored 26 systems, including every broker interface and