llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp
38Vexday Risk Score
No sign of exploitation. It has a public proof of concept.
ssvc Attendcvss 8.5
from disclosure to weapon1 days
Published on NVDAug 6
1st PoC+1d
exploitation probability
—
observed exploitation
nono source reports it
1 public exploit(s)
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.
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Affected products
ggml-org · llama.cpppublic PoCs found — 1
githubgithub.com/Hunt-Benito/one-multiply-too-many-cve-2026-70638-llama-cpp-android-jni-integer-overflow★ 0⚠ Public resources, to assess the exposure of systems you control or are authorized to test. Test only with authorization.
References
https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9d9388https://github.com/ggml-org/llama.cpp/releases/tag/b7446https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patcheshttps://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-integer-overflow-via-new-1batch-in-llama-android-cpp