Vulnerability · Published Aug 6, 2026 · Assigned by VulnCheck

CVE-2026-43631llama.cpp b7492–b9060 Use-After-Free RCE via llama-server

High 8.1

In plain English

A high-severity use-after-free in llama.cpp from ggml-org. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.6% (higher than 48% of all known vulnerabilities).

Severity (CVSS 3.1)8.1High

Exploit odds (30 days)0.6%top 52.5% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official description

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 packages & fixed versions

Ecosystem	Package	Fixed in	Advisory
Debian:14	llama.cpp	no fix listed	DEBIAN-CVE-2026-43631
Ubuntu:26.04:LTS	llama.cpp	no fix listed	UBUNTU-CVE-2026-43631
Ubuntu:26.10	llama.cpp	no fix listed	UBUNTU-CVE-2026-43631

Affected products (as reported)

Vendor	Product	Versions
ggml-org	llama.cpp	b7492 – through b9060

Weakness: CWE-416, CWE-362 · Vector: CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H

References

https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches mitigation
https://www.vulncheck.com/advisories/llama-cpp-b7492-b9060-use-after-free-rce-via-llama-server third-party-advisory