CVE-2026-70640: Ggml Llama.cpp

High severity, CVSS 7.0. EPSS: 0.2% chance of exploitation in the next 30 days.

llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench_1model() and free_1context() lack synchronization, allowing Thread A to operate on freed memory while Thread B concurrently frees the llama_context. Attackers can exploit this by performing heap spray with attacker-controlled data containing a fake vtable to hijack the vtable pointer at offset +0x30, causing llama_batch_allocr::clear() to dereference arbitrary memory and achieve remote code execution.

Affected products

• Ggml Llama.cpp: from b1886, up to and including b7445

Published 2026-08-06. Last modified 2026-09-21.