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.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-122",
"CWE-190"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/70xxx/CVE-2026-70638.json"
}{
"extracted_events": [
{
"cpe": "cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*",
"range": [
{
"introduced": "b1886"
},
{
"last_affected": "b7445"
}
],
"source": "CPE_RANGE"
},
{
"range": [
{
"fixed": "5c0d18881e0e9794c96b2602736b758bac9d9388"
}
],
"source": "REFERENCES_COMMIT"
},
{
"original_tag": "b7446",
"range": [
{
"fixed": "5c0d18881e0e9794c96b2602736b758bac9d9388"
}
],
"source": "REFERENCES_TAG"
}
]
}