CVE-2026-70640
llama.cpp builds b1886 through b7445 contain a race condition …
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 now
- Check your exposureFind out whether the affected software runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
- github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388
- github.com/ggml-org/llama.cpp/releases/tag/b7446
- www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama
- www.cyera.com/research/breaking-local-ai-runtimes-10-vulnerabilities-in-the-engine-behind-
- www.youtube.com/watch?v=_FKX5hDwgVE&t=1079s
- nvd.nist.gov/vuln/detail/CVE-2026-70640
- cve.org/CVERecord?id=CVE-2026-70640
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.