CVE-2026-70638 llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp

High 8.5 Published Updated

Integer overflow in llama.cpp Android JNI wrapper allows attackers to cause heap corruption and execute arbitrary code via crafted model files.

Exploited in the wild
Not known
Login needed
Not needed
Attackable
Local or same network only
Victim action needed
A user has to click or open something
Fix
Available

What is CVE-2026-70638?

CVE-2026-70638 is a high-severity vulnerability in ggml-org llama.cpp, published on 6 Aug 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.

Official description

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.

Weakness: CWE-190, CWE-122

Which versions are affected by CVE-2026-70638?

It affects 1 product.

Products include Ggml Llama.cpp.

How do I fix CVE-2026-70638?

Apply the vendor's patch.

Is CVE-2026-70638 being exploited?

There is no known exploitation of CVE-2026-70638 in the wild and no public exploit code.

Public exploit code: 1 proofs of concept on GitHub.

Sources

Also known as DEBIAN-CVE-2026-70638, GHSA-p56f-gv6x-v6mg.

Is CVE-2026-70638 in your software?

Upload an SBOM and sbomify checks it against every vulnerability here, every day.

Check your SBOMs for free