Vulnerability 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.
CVSS Score
HIGH
Related Weaknesses (CWE)
References
- https://github.com/Vladimir-tokarev-cyera/llama-cpp-security-patches
- https://github.com/ggml-org/llama.cpp/commit/5c0d18881e0e9794c96b2602736b758bac9
- https://github.com/ggml-org/llama.cpp/releases/tag/b7446
- https://www.vulncheck.com/advisories/llama-cpp-b1886-b7445-integer-overflow-via-
FAQ
What is CVE-2026-70638?
CVE-2026-70638 is a vulnerability with a CVSS score of 7.8 (HIGH). 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-controlle...
How severe is CVE-2026-70638?
CVE-2026-70638 has been rated HIGH with a CVSS base score of 7.8/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-70638?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.