← Vulnerability feed

Vulnerability record · CVE-2026-70640 · published 6 August 2026

CVE-2026-70640: Ggml llama.cpp race condition vulnerability

Ggml · Llama.Cpp

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.

7.3 CVSS 4.0 High EPSS 0.24% · top 86.4% CWE-362 · Race conditionCWE-476 · NULL pointer dereference
7.3CVSS 4.0 base score
0.24%EPSS exploitation probability, 30 days
NoNot in CISA KEV
1Affected product versions listed by NVD
4References, 1 tagged exploit
21 Sep 2026Last modified by 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.

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:

Affected products

1 vulnerable configurations from NVD's CPE data, grouped by vendor and product.

References

LinkTags
https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches PatchThird Party Advisory
https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388 Patch
https://github.com/ggml-org/llama.cpp/releases/tag/b7446 PatchRelease NotesVendor Advisory
https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-race-condition-use-after-free-via-llama-android-cpp ExploitThird Party Advisory

Track CVE-2026-70640 inside VULONE

Watch it alongside the ransomware crews, C2 infrastructure and forum chatter that reference it, query it through the API and pull it into your SIEM over TAXII.

Start free Open in platform

Related vulnerabilities

Same products first, then exploited flaws of the same weakness class.

9.8CVE-2026-34159Ggml llama.cpp memory buffer overflow vulnerabilityllama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation …EPSS 1.2%9.8CVE-2026-21869Ggml llama.cpp out-of-bounds write vulnerabilityllama.cpp is an inference of several LLM models in C/C++. In commits 55d4206c8 and prior, the n_discard parameter is parsed directly from JSON input …EPSS 0.52%9.8CVE-2024-42478Ggml llama.cpp out-of-bounds read vulnerabilityllama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address reading. This v…EPSS 0.60%9.8CVE-2024-42479Ggml llama.cpp out-of-bounds write vulnerabilityllama.cpp provides LLM inference in C/C++. The unsafe `data` pointer member in the `rpc_tensor` structure can cause arbitrary address writing. This v…EPSS 2.6%9.8CVE-2024-23605Ggml llama.cpp integer overflow vulnerabilityA heap-based buffer overflow vulnerability exists in the GGUF library header.n_kv functionality of llama.cpp Commit 18c2e17. A specially crafted .ggu…EPSS 1.3%9.8CVE-2024-23496Ggml llama.cpp integer overflow vulnerabilityA heap-based buffer overflow vulnerability exists in the GGUF library gguf_fread_str functionality of llama.cpp Commit 18c2e17. A specially crafted .…EPSS 1.3%9.8CVE-2024-21802Ggml llama.cpp heap-based buffer overflow vulnerabilityA heap-based buffer overflow vulnerability exists in the GGUF library info->ne functionality of llama.cpp Commit 18c2e17. A specially crafted .ggu…EPSS 1.4%9.8CVE-2024-21825Ggml llama.cpp integer overflow vulnerabilityA heap-based buffer overflow vulnerability exists in the GGUF library GGUF_TYPE_ARRAY/GGUF_TYPE_STRING parsing functionality of llama.cpp Commit 18c2…EPSS 1.3%

Source: NIST National Vulnerability Database (record CVE-2026-70640), CISA KEV, FIRST EPSS (scores of 2026-09-26). This page is refreshed as NVD updates the record.