CVE-2026-70638High· 7.8▾ MidnightPoC availablellama.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 overflo…
▾ Midnight zone — Critical, or high with PoC / in-the-wild
impact 42.9 · likelihood 0 · exploitation 12
A public proof-of-concept already exists for this vulnerability — see Exploit availability below.
Public exploit / PoC code seen in 1 source. Availability, not in-the-wild use.
Exploit-prediction probability, daily snapshots since Sep 21.
Disclosure to exploitation, from the record and what we observed since indexing it.
Disclosed via NVD
Last analysed / modified upstream
0.2%
0.2% → 0.2%
1 GitHub repo (last check)
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.
llama.cpp >= b1886, <= b7445Refer to the linked advisories for vendor-supplied fixes and affected version ranges.
Connected by shared product, vendor, weakness, or advisory.
CVE-2026-70639Medium· 5.5llama.cpp builds b1886 through b7445 contain a null pointer dereference vulnerability in the LLaMA-Android JNI wrapper where the bench_1model() function fails to validate the model context pointer before dereferencing it
CVE-2026-70640High· 7.0llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench_1model() and free_1context() lack synchronization, allowing Thread A to operate on freed memory while…
CVE-2026-43622High· 7.8llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new_1batch() allocates memory using malloc() while free_1batch() deallocates it using the C++ delete operator, causing heap m…
CVE-2026-43629High· 8.1llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking, allowing attackers with write access…
CVE-2026-43627High· 7.8llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llama_batch_init() function where unchecked multiplications in malloc() calls can wrap past INT32_MAX when computing allocation sizes
CVE-2026-116840Medium· 6.1llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader