Vulnerabilidad · Publicado 16/09/2026
LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen offsets in the leaf_depth_ buffer during feature contribution computation.
LightGBM through 4.7.0 fails to validate child and split array values when parsing text models, allowing attackers to write out-of-bounds memory during SHAP prediction. Attackers can craft malicious model files with invalid node references that trigger out-of-bounds writes at attacker-chosen offsets in the leaf_depth_ buffer during feature contribution computation.
Score: 7.8/10 — Severidad: HIGH — Estado NIST: Received
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
CWE-787
Publicado en NIST NVD.