LATIDIA · Ciberseguridad
Más allá del parche: reconstrucción de una elusión de parche de solución incompleta en marcos de agentes de LLM con sondas benignas controladas
arXiv:2611.20514v1 Tipo de anuncio: nuevo Resumen: Volver a ejecutar la prueba de concepto original de una vulnerabilidad después de aplicar un parche permite comprobar si el desencadenante notificado sigue siendo reproducible, pero no establece que la vulnerabilidad subyacente...
WhatsApp ↗Telegram ↗
La noticia
arXiv:2611.20514v1 Announce Type: new Abstract: Replaying a vulnerability's original proof-of-concept after patching tests whether its reported trigger remains reproducible, but does not establish that the underlying security invariant holds on other code paths. We present a benign, control-gated reconstruction method and a pilot study across four LLM agent frameworks and four invariant classes. For PraisonAI, we compare original-trigger replay (B0) with a distinct sibling-path probe (M). We also perform five before/after reconstructions across Langroid, Agno, and CrewAI. Each run reports VIOLATION, NO_VIOLATION_OBSERVED, or INCONCLUSIVE, gated by a positive authorized control. Probes use inert markers or builtins-reachability checks. At PraisonAI 4.6.31, the original tool-loading trigger is blocked while the tool_override path