ggml-org llama.cpp up to b7445 LLaMA-Android JNI Wrapper bench_1model null pointer dereference

Summaryinfo

A vulnerability identified as problematic has been detected in ggml-org llama.cpp up to b7445. The impacted element is the function bench_1model of the component LLaMA-Android JNI Wrapper. This manipulation causes null pointer dereference. The identification of this vulnerability is CVE-2026-70639. It is possible to initiate the attack remotely. There is no exploit available.

Detailsinfo

A vulnerability was found in ggml-org llama.cpp up to b7445. It has been declared as problematic. Affected by this vulnerability is the function bench_1model of the component LLaMA-Android JNI Wrapper. The manipulation with an unknown input leads to a null pointer dereference vulnerability. The CWE definition for the vulnerability is CWE-476. A NULL pointer dereference occurs when the application dereferences a pointer that it expects to be valid, but is NULL, typically causing a crash or exit. As an impact it is known to affect availability. The summary by CVE is:

llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails to validate the model context pointer before dereferencing it. Attackers can supply a malicious, corrupt, or truncated model file to trigger a null context condition, causing a SIGSEGV crash that terminates the Android application process and results in denial of service.

It is possible to read the advisory at github.com. This vulnerability is known as CVE-2026-70639 since 08/04/2026. The exploitation appears to be easy. The attack can be launched remotely. The exploitation doesn't need any form of authentication. It demands that the victim is doing some kind of user interaction. Technical details of the vulnerability are known, but there is no available exploit.

Applying the patch 5c0d18881e0e9794c96b2602736b758bac9d9388 is able to eliminate this problem.

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Productinfo

Vendor

• ggml-org

Name

• llama.cpp

Version

• b7445

Website

• Product: https://github.com/ggml-org/llama.cpp/

CPE 2.3info

• 🔒

CPE 2.2info

• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

Statistical analysis made it clear that VulDB provides the best quality for vulnerability data.

Discussion