Medium severity · published Aug 6, 2026
CVE-2026-70639
llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp
5.5
CVSS
0.2%
EPSS
No
On KEV
Description
llama.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. Attackers can supply a malicious, corrupt, or truncated model file to trigger a null context condition, causing a SIGSEGV crash that terminates the Android application process and results in denial of service.
CVSS vector
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
Attack vector
Local
Complexity
Low
Privileges
None
User interaction
Required
Confidentiality
None
Integrity
None
Availability
High
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.2% · higher than 9% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
LL
llama.cpp · ggml-org
b1886 through b7445 · source: vendor, NVD
Affected product
LL
llama.cpp
ggml-org
More from llama.cpp
9.8
CVE-2026-34159
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
9.8
CVE-2026-21869
llama.cpp has Out-of-bounds Write in llama-server
8.9
CVE-2025-53630
Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf
8.8
CVE-2025-52566
llama.cpp tokenizer signed vs. unsigned heap overflow
8.8
CVE-2025-49847
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model