7.8High

CVE-2026-43627llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function

ggml-org llama.cpp Published: (3 months ago)

Description

llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where unchecked multiplications in malloc() calls can wrap past INT32_MAX when computing allocation sizes. Attackers can pass specially crafted parameters to trigger integer overflow, causing heap corruption and potentially achieving arbitrary code execution through subsequent batch operations that write past allocated buffer boundaries.

Weakness (CWE): CWE-190CWE-680

Data: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Published as the sources state it, in English.

Affected products and versions

VendorProductVersions
ggml llama.cpp b1283 – ≤ b9058
ggml-org llama.cpp b1283 – ≤ b9058

References and patches

CPE matches (NVD) (1)

  • cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:* ≥ b1283 ≤ b9058