---
id: CVE-2026-70638
title: >-
  llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability
  in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies
  sizeof(llama_seq_id) by an attacker-controlled n_seq_max parameter without
  overflo…
summary: >-
  llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability
  in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies
  sizeof(llama_seq_id) by an attacker-controlled n_seq_max parameter without
  overflo…
severity: high
cvss: 7.8
cvssVector: 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H'
cwe:
  - CWE-122
  - CWE-190
vendor: ggml
product: llama.cpp
affected:
  - 'llama.cpp >= b1886, <= b7445'
published: '2026-08-06'
updated: '2026-09-21'
sourceUpdated: '2026-09-21T18:11:01.283'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-70638'
references:
  - url: 'https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches'
    label: disclosure@vulncheck.com
  - url: >-
      https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388
    label: disclosure@vulncheck.com
  - url: 'https://github.com/ggml-org/llama.cpp/releases/tag/b7446'
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-integer-overflow-via-new-1batch-in-llama-android-cpp
    label: disclosure@vulncheck.com
tags:
  - nvd
  - exploit-available
epss: 0.00231
epssPercentile: 0.12419
exploits:
  github: 1
  githubRepos:
    - >-
      https://github.com/Hunt-Benito/one-multiply-too-many-cve-2026-70638-llama-cpp-android-jni-integer-overflow
  checkedAt: '2026-09-26T09:05:57.665Z'
exploitAvailable: true
ingestedAt: '2026-09-21T18:50:57.546Z'
---

## Overview

llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies sizeof(llama_seq_id) by an attacker-controlled n_seq_max parameter without overflow validation, causing heap buffer allocation to wrap and allocate insufficient memory. Attackers can exploit this by providing a crafted n_seq_max value through a malicious model file or JNI call to trigger heap corruption and achieve denial of service or arbitrary code execution on Android applications using the LLaMA-Android binding.

## Affected

- `llama.cpp >= b1886, <= b7445`

## Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.