ggml-org llama.cpp DRY sampler dry_allowed_length integer underflow

Summaryinfo

A vulnerability was found in ggml-org llama.cpp and classified as critical. The affected element is an unknown function of the component DRY sampler. Such manipulation of the argument dry_allowed_length leads to integer underflow. This vulnerability is referenced as CVE-2026-43628. It is possible to launch the attack remotely. No exploit is available.

Detailsinfo

A vulnerability was found in ggml-org llama.cpp (the affected version is unknown). It has been rated as critical. Affected by this issue is an unknown code of the component DRY sampler. The manipulation of the argument dry_allowed_length with an unknown input leads to a integer underflow vulnerability. Using CWE to declare the problem leads to CWE-191. The product subtracts one value from another, such that the result is less than the minimum allowable integer value, which produces a value that is not equal to the correct result. Impacted is confidentiality, integrity, and availability. CVE summarizes:

llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with dry_allowed_length set to INT32_MIN to the /v1/completions or /v1/chat/completions endpoints. Attackers can exploit this vulnerability to crash the server with SIGSEGV causing denial of service for all connected users, or corrupt token sampling probabilities by reading garbage values from memory before the allocated buffer.

The advisory is available at github.com. This vulnerability is handled as CVE-2026-43628 since 05/01/2026. The exploitation is known to be easy. The attack may be launched remotely. No form of authentication is required for exploitation. Technical details are known, but there is no available exploit. The structure of the vulnerability defines a possible price range of 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 best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Vendor

• ggml-org

Name

• llama.cpp

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion