CVE-2026-43631

High

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.

SeverityHigh

CVSS8.1

Exploit probability—

ProductGgml Llama.cpp

PublishedAug 6, 2026

First seenAug 6, 2026

Weakness typeCWE-416Use after free CWE-362Race condition

How to fix

Vendor advisories

github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches

Affected products

Product	Affected versions	Fixed in
ggml llama.cpp	b7492 ≤ v ≤ b9060	—

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.