LATIDIA · Ciberseguridad

ToFu: Explotar y difuminar el límite de LLM-Orchestrator-Tool Trust

arXiv:2610.13651v1 Anuncio Tipo: nuevo Resumen: Los modelos de lenguaje grandes (LLM) se implementan cada vez más como agentes que interactúan con software externo a través de herramientas, con una capa de orquestación que traduce las salidas del modelo.

La noticia

arXiv:2610.13651v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents that interact with external software through tools, with an orchestration layer translating model outputs into structured tool invocations. This architecture creates an LLM-orchestrator-tool trust boundary where tool semantics may go unenforced and LLM-generated arguments may be incorrectly treated as trusted. We present ToFu, a tool-aware framework that automatically derives semantic security checks for LLM tools from their existing metadata and a CWE-guided sanitizer corpus. ToFu specializes these checks to individual tools and automatically generates fuzzing harnesses and semantic oracles using runtime introspection and outcome sanitization. We evaluated ToFu across 273 MCP servers containing 3405 tools and