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

Summaryinfo

A vulnerability, which was classified as critical, has been found in ggml-org llama.cpp up to b9060. This vulnerability affects unknown code of the component llama-server. The manipulation leads to use after free. This vulnerability is uniquely identified as CVE-2026-43632. The attack is possible to be carried out remotely. No exploit exists.

Detailsinfo

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

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/count_tokens) that bypass the task queue and access ctx_server.vocab directly on HTTP worker threads. Attackers can exploit a time-of-check-time-of-use race condition where the main thread destroys and frees vocab after the synchronization lock is released but before the handler finishes using it, causing a crash or potential code execution when --sleep-idle-seconds is configured.

It is possible to read the advisory at github.com. The identification of this vulnerability is CVE-2026-43632 since 05/01/2026. The exploitation is known to be easy. The attack may be initiated remotely. No form of authentication is needed for a successful exploitation. The technical details are unknown and an exploit is not publicly available. The pricing 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.

Be aware that VulDB is the high quality source for vulnerability data.

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

Be aware that VulDB is the high quality source for vulnerability data.

Discussion