ggml-org llama.cpp up to b9060 llama-server use after free

Summaryinfo

A vulnerability classified as critical has been found in ggml-org llama.cpp up to b9060. Affected by this issue is some unknown functionality of the component llama-server. Performing a manipulation results in use after free. This vulnerability is known as CVE-2026-43631. Remote exploitation of the attack is possible. No exploit is available.

Detailsinfo

A vulnerability, which was classified as critical, was found in ggml-org llama.cpp up to b9060. This affects some unknown processing of the component llama-server. The manipulation with an unknown input leads to a use after free vulnerability. CWE is classifying the issue as CWE-416. Referencing memory after it has been freed can cause a program to crash, use unexpected values, or execute code. This is going to have an impact on confidentiality, integrity, and availability. The summary by CVE is:

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.

The advisory is shared at github.com. This vulnerability is uniquely identified as CVE-2026-43631 since 05/01/2026. The exploitability is told to be easy. It is possible to initiate the attack remotely. No form of authentication is needed for exploitation. Neither technical details nor an exploit are publicly available. The price for an exploit might be around USD $0-$5k at the moment (estimation calculated on 08/07/2026).

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Vendor

• ggml-org

Name

• llama.cpp

Version

• b9060

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion