Vulnerability details

CVE-2026-70640

ggml-org llama.cpp

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

CVSS 4.0

7.3High

Official 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 scores

Score	Version	Source	Vector
7.3High	4.0	CVEProject cvelistV5 (CNA) (VulnCheck)	`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`
7.0High	3.1	CVEProject cvelistV5 (CNA) (VulnCheck)	`CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H`

Affected products

Vendor	Product	Versions	Source
ggml-org	llama.cpp	b1886 ≤ v ≤ b7445	CVEProject cvelistV5 (CNA)

References and advisories

Kolun on Telegram @kolunsec Exploited CVEs, key news and a daily digest Alerts for this product's next CVEsFollow the product to get new vulnerabilities on Telegram.

Details

Published: 2026-08-06
Last updated: 2026-11-08
State: Published
Assigner (CNA): VulnCheck

Exploit prediction (EPSS)

0.24%

Probability of exploitation in 30 days

15.1%

Percentile (among all CVEs)

SSVC assessment (CISA)

Automatable: No
Exploitation: None
Technical impact: Total

Weaknesses (CWE)

CWE-476
NULL Pointer Dereference
CWE-362
Concurrent Execution using Shared Resource with Improper Synchronization ('Race Condition')