LATIDIA · Ciberseguridad

Escaneo del arnés: un estudio de repositorio de exposiciones de configuración en agentes de codificación de IA

arXiv: 2609.07360v2Announce Type: replace-cross Abstract: Los agentes de codificación de IA se basan en instrucciones de repositorio, habilidades, ganchos, declaraciones de servidor de herramientas y definiciones de subagentes. Estos artefactos distribuyen tanto el comportamiento como

La noticia

arXiv:2609.07360v2 Announce Type: replace-cross Abstract: AI coding agents rely on repository instructions, skills, hooks, tool-server declarations, and subagent definitions. These artifacts distribute both behavior and access to executable dependencies, making configuration review part of the agent software supply chain. We study 3,171 public GitHub repositories: 2,660 assembled setups and 511 skill collections. Deterministic analysis, mechanical re-derivation, model-assisted review, and platform documentation checks identify six categories of configuration exposure and conformance issues. Unpinned MCP package declarations occur in 9.8% of setups, broad execution grants in 2.5%, and broad skill tool preapproval in 3.8%. Their union covers 409 setups (15.4%); among setups with MCP configuration, 24.5% contain an unpinned declaration. Including required-field