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
ggml: llama.cpp
References4
- github.com/ggml-org/llama.cpp/releases/tag/b7446 PatchRelease NotesVendor Advisory
- github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches PatchThird Party Advisory
- github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b260273… Patch
- www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-conditi… ExploitThird Party Advisory
Metrics
- CVSS 3.1
-
7.0
HIGH
Score source: CNA
CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H - CVSS 4.0
-
7.3
HIGH
Score source: CNA
CVSS:4.0/AV:L/AC:H/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X - EPSS — exploit probability
- 0% percentile: 15 · as of 12 November 2026
- CWE
- CWE-362CWE-476
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.