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.
Published: 2026-08-06
Score: 7.3 High
EPSS: < 1% Very Low
KEV: No
Impact: n/a
Action: n/a
AI Analysis

Analysis and contextual insights are available on OpenCVE Cloud.

Remediation

No vendor fix or workaround currently provided.

Additional remediation guidance may be available on OpenCVE Cloud.

Tracking

Sign in to view the affected projects.

Advisories

No advisories yet.

History

Fri, 14 Aug 2026 17:15:00 +0000

Type Values Removed Values Added
First Time appeared Ggml
Ggml llama.cpp
CPEs cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*
Vendors & Products Ggml
Ggml llama.cpp

Fri, 07 Aug 2026 19:15:00 +0000


Fri, 07 Aug 2026 17:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}


Fri, 07 Aug 2026 02:15:00 +0000

Type Values Removed Values Added
First Time appeared Ggml-org
Ggml-org llama.cpp
Vendors & Products Ggml-org
Ggml-org llama.cpp

Thu, 06 Aug 2026 22:15:00 +0000

Type Values Removed Values 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.
Title llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp
Weaknesses CWE-362
CWE-476
References
Metrics cvssV3_1

{'score': 7, 'vector': 'CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H'}

cvssV4_0

{'score': 7.3, 'vector': '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'}


Subscriptions

Ggml-org Llama.cpp
cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-08-14T16:51:39.415Z

Reserved: 2026-08-04T20:17:18.298Z

Link: CVE-2026-70640

cve-icon Vulnrichment

Updated: 2026-08-07T16:18:35.311Z

cve-icon NVD

Status : Received

Published: 2026-08-06T22:18:28.927

Modified: 2026-08-07T19:18:53.680

Link: CVE-2026-70640

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-08-07T02:00:06Z

Weaknesses