High severity7.0NVD Advisory· Published Aug 6, 2026· Updated Oct 29, 2026
CVE-2026-70640
CVE-2026-70640
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
3Patches
Vulnerability mechanics
References
3- github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388nvdPatch
- github.com/ggml-org/llama.cpp/releases/tag/b7446nvdPatchRelease NotesVendor Advisory
- www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cppnvdExploitThird Party Advisory
News mentions
0No linked articles in our index yet.