---
id: CVE-2026-43631
title: >-
  llama.cpp builds b7492 through the latest b9060 contains a use-after-free
  vulnerability in the vocab pointer of llama-server when the
  --sleep-idle-seconds feature is enabled, allowing unauthenticated remote
  attackers to execute arbitrary…
summary: >-
  llama.cpp builds b7492 through the latest b9060 contains a use-after-free
  vulnerability in the vocab pointer of llama-server when the
  --sleep-idle-seconds feature is enabled, allowing unauthenticated remote
  attackers to execute arbitrary…
severity: high
cvss: 8.1
cvssVector: 'CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H'
cwe:
  - CWE-362
  - CWE-416
  - CWE-362
  - CWE-416
vendor: ggml
product: llama.cpp
affected:
  - 'llama.cpp >= b7492, <= b9060'
published: '2026-08-06'
updated: '2026-09-21'
sourceUpdated: '2026-09-21T18:11:21.397'
source: NVD
sourceUrl: 'https://nvd.nist.gov/vuln/detail/CVE-2026-43631'
references:
  - url: 'https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches'
    label: disclosure@vulncheck.com
  - url: >-
      https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-rce-via-llama-server
    label: disclosure@vulncheck.com
tags:
  - nvd
epss: 0.00421
epssPercentile: 0.36073
ingestedAt: '2026-09-21T18:50:57.545Z'
---

## Overview

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary code. Attackers can trigger the vulnerability by sending requests to affected endpoints while the server transitions to sleep mode, causing concurrent worker threads to dereference a freed vocab pointer that can be reclaimed with attacker-controlled data to achieve remote code execution.

## Affected

- `llama.cpp >= b7492, <= b9060`

## Remediation

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