CVE-2026-70640

High

Description

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.

SeverityHigh

CVSS7.0

Exploit probability—

ProductGgml Llama.cpp

PublishedAug 6, 2026

First seenAug 6, 2026

Weakness typeCWE-476NULL pointer dereference CWE-362Race condition

How to fix

Patches

github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388

Vendor advisories

github.com/ggml-org/llama.cpp/releases/tag/b7446

Affected products

Product	Affected versions	Fixed in
ggml llama.cpp	b1886 ≤ v ≤ b7445	—

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.