LATIDIA · Ciberseguridad
Tenemos todas las cartas: cómo proteger las tarjetas de los agentes en el límite de confianza operativa del protocolo Agent2Agent
arXiv:2611.18887v1 Tipo de anuncio: nuevo Resumen: Los protocolos de interoperabilidad de agentes de IA permiten a los orquestadores descubrir e invocar agentes externos utilizando metadatos legibles por máquina. En el protocolo Agent2Agent (A2A), el agente Ca
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.18887v1 Announce Type: new Abstract: AI agent interoperability protocols enable orchestrators to discover and invoke external agents using machine-readable metadata. In the Agent2Agent (A2A) protocol, Agent Cards contain attacker-controllable natural-language fields that may influence agent selection before a provider is invoked, creating a pre-invocation trust problem. We characterize this discovery-time attack surface through a taxonomy of ten Agent Card manipulation attacks and present SECCARD, a layered validation framework combining protocol checks, deterministic analysis, and LLM-based semantic reasoning. We measure the emerging public A2A ecosystem by probing 36.1 million Internet domains and collecting 310 deployed Agent Cards. Two annotators independently label the corpus with 96.8% agreement. We then construct a 660-card