- CVSS
- HIGH · 7v3.1CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
- Published
- 2026-08-06
- Weakness
- CWE-362, CWE-476
- Source
- nvd.nist.gov/vuln/detail/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.
References
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
- https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388
- https://github.com/ggml-org/llama.cpp/releases/tag/b7446
- https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cpp
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-70640 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.