CVE-2026-70640: llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI…
CVE-2026-70640 · Severity: high · CVSS 7 · Published 2026-08-06
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.
No. Junglewise Threat Intelligence has no report of CVE-2026-70640 being exploited in the wild.
How severe is CVE-2026-70640?
High severity, with a CVSS score of 7, published 6 August 2026.
Which products and versions are affected?
GGML Llama.Cpp. The advisory does not name versions.
Is there a fix for CVE-2026-70640?
No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.
Am I affected by CVE-2026-70640?
Check whether you run GGML Llama.Cpp. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.