ggml-org llama.cpp up to 0.17.1/b7445 LLaMA-Android JNI Wrapper new_1batch n_seq_max integer overflow

Summaryinfo

A vulnerability, which was classified as critical, was found in ggml-org llama.cpp up to 0.17.1/b7445. Affected by this vulnerability is the function new_1batch of the component LLaMA-Android JNI Wrapper. The manipulation of the argument n_seq_max results in integer overflow. This vulnerability is reported as CVE-2026-70638. The attack can be launched remotely. No exploit exists.

Detailsinfo

A vulnerability classified as critical has been found in ggml-org llama.cpp up to 0.17.1/b7445. Affected is the function new_1batch of the component LLaMA-Android JNI Wrapper. The manipulation of the argument n_seq_max with an unknown input leads to a integer overflow vulnerability. CWE is classifying the issue as CWE-190. The product performs a calculation that can produce an integer overflow or wraparound, when the logic assumes that the resulting value will always be larger than the original value. This can introduce other weaknesses when the calculation is used for resource management or execution control. This is going to have an impact on confidentiality, integrity, and availability. CVE summarizes:

llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new_1batch() function multiplies sizeof(llama_seq_id) by an attacker-controlled n_seq_max parameter without overflow validation, causing heap buffer allocation to wrap and allocate insufficient memory. Attackers can exploit this by providing a crafted n_seq_max value through a malicious model file or JNI call to trigger heap corruption and achieve denial of service or arbitrary code execution on Android applications using the LLaMA-Android binding.

The advisory is shared for download at github.com. This vulnerability is traded as CVE-2026-70638 since 08/04/2026. The exploitability is told to be easy. It is possible to launch the attack remotely. The exploitation doesn't require any form of authentication. Successful exploitation requires user interaction by the victim. There are known technical details, but no exploit is available.

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

Once again VulDB remains the best source for vulnerability data.

Productinfo

Vendor

• ggml-org

Name

• llama.cpp

Version

• 0.17.0
• 0.17.1
• 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

Once again VulDB remains the best source for vulnerability data.

Discussion