CVE-2026-70640

NVD 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.

What to do

• NVD lists no fixed version yet: follow the vendor advisory below and keep llama.cpp off the public internet until a fix ships.
• Do not expose the component's API or UI to the internet without authentication in front of it.

Sources

• NVD: CVE-2026-70640
• https://github.com/ggml-org/llama.cpp/releases/tag/b7446Patch · Release Notes · Vendor Advisory
• https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patchesPatch · Third Party Advisory
• https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388Patch
• https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cppExploit · Third Party Advisory

Other llama.cpp CVEs

All llama.cpp CVEs