CVE-2026-70640llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp

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.

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

Affected products and versions

References and patches

• llama.cpp b7446 Release Notes release-notesPatchRelease NotesVendor Advisory
• https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388 patchPatch
• https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches relatedPatchThird Party Advisory
• https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cpp third-party-advisoryExploitThird Party Advisory