CVE-2026-70640

HIGH 7.0

llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp

CVSS Score

7.0

EPSS Score

0.0%

EPSS Percentile

0th

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.

CWE	CWE-476 CWE-362
Vendor	ggml-org
Product	llama.cpp
Published	Aug 6, 2026
Last Updated	Aug 6, 2026

Stay Ahead of the Next One

Get instant alerts for ggml-org llama.cpp

Be the first to know when new high vulnerabilities affecting ggml-org llama.cpp are published — delivered to Slack, Telegram or Discord.

Get Free Alerts → Free · No credit card · 60 sec setup

CVSS v3 Breakdown

CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack Vector

Local

Attack Complexity

High

Privileges Required

None

User Interaction

Required

Scope

Unchanged

Confidentiality

High

Integrity

High

Availability

High

Affected Versions

ggml-org / llama.cpp

b1886 ≤ b7445 0.9.0 ≤ 0.17.1

References

NVD ↗ CVE.org ↗ EPSS Data ↗

github.com: https://github.com/ggml-org/llama.cpp/releases/tag/b7446 github.com: https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388 github.com: https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches

Credits

Vladimir Tokarev (@G1ND1L4) - Vulnerability Research Tech Lead, Cyera Ofek Itach (@ofekitach) - Security Research Team Lead, Cyera