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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| ggml-org | llama.cpp | b1886 – ≤ b7445 | — |
Fixed in Linux distributions
Distributions backport fixes, so the version that fixes this vulnerability differs per release — upgrade to at least the version shown. From the distributions' security trackers and advisories.
Debian
Security tracker ↗| Release | Package | Fixed in | Advisory |
|---|---|---|---|
| Debian 14 | llama.cpp | 7593+dfsg-1 | — |
References
- llama.cpp b7446 Release Notes release-notes
- https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388 patch
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches related
- https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cpp third-party-advisory