LATIDIA · Ciberseguridad

Lavado de aprobaciones: sistematización de la aprobación: fallas vinculantes de ejecución en los arneses de agentes de codificación de IA

arXiv: 2609.38983v1Tipo de anuncio: nuevo Resumen: Los arneses modernos de agentes de codificación de IA (Claude Code, Codex CLI, Cursor) descansan su límite de seguridad en una suposición en gran parte no examinada: que la acción que un humano aprueba es la

La noticia

arXiv:2609.38983v1 Announce Type: new Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a human approves is the same action A' the harness executes, where A is fixed by a stated policy for what a scope grant or session-scoped approval authorizes. We show this assumption fails systematically and reproducibly. We introduce Approval Laundering, a taxonomy of six failure modes by which a harness's enforcement mechanism silently substitutes A' for A after approval: Scope, Argument, Temporal, Tool, Delegation, and Semantic laundering. Unlike prior work that evaluates risk classifiers against static corpora or infers implicit authorization boundaries, we