7.3
HIGH CVSS 4.0
CVE-2026-70640
llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp
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.

INFO

Published Date :

Aug. 6, 2026, 10:18 p.m.

Last Modified :

Aug. 6, 2026, 10:18 p.m.

Remotely Exploit :

No
Affected Products

The following products are affected by CVE-2026-70640 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

No affected product recoded yet

CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 HIGH 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 3.1 HIGH [email protected]
CVSS 4.0 HIGH 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 4.0 HIGH [email protected]
Solution
Synchronize access to shared resources in the LLaMA-Android JNI wrapper to prevent race conditions.
  • Implement proper locking mechanisms in bench_1model and free_1context.
  • Ensure thread-safe access to the llama_context.
  • Apply vendor patches when available.
  • Review and test synchronization logic.
References to Advisories, Solutions, and Tools

Here, you will find a curated list of external links that provide in-depth information, practical solutions, and valuable tools related to CVE-2026-70640.

URL Resource
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
CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorizes the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-70640 is associated with the following CWEs:

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-70640 weaknesses.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-70640 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-70640 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • New CVE Received by [email protected]

    Aug. 06, 2026

    Action Type Old Value New Value
    Added Affected [{'vendor': 'ggml-org', 'product': 'llama.cpp', 'versions': [{'status': 'affected', 'version': 'b1886', 'versionType': 'custom', 'lessThanOrEqual': 'b7445'}, {'status': 'affected', 'version': '0.9.0', 'versionType': 'semver', 'lessThanOrEqual': '0.17.1'}, {'status': 'unaffected', 'version': '5c0d18881e0e9794c96b2602736b758bac9d9388', 'versionType': 'git'}], 'defaultStatus': 'unaffected'}]
    Added 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.
    Added CVSS V4.0 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
    Added CVSS V3.1 AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H
    Added CWE CWE-362
    Added CWE CWE-476
    Added Reference https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388
    Added Reference https://github.com/ggml-org/llama.cpp/releases/tag/b7446
    Added Reference https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.