Skip to content
Ggml vulnerabilities
Newest
-
ggml llama.cpp
llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers...
CVE-2026-52132
Fix available
7.5 High
-
ggml llama.cpp
llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.
CVE-2026-52131
7.5 High
-
ggml llama.cpp
llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to...
CVE-2026-52130
7.5 High
-
ggml llama.cpp
llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints
CVE-2026-43632
9.2 Critical
-
ggml llama.cpp
llama.cpp b7492–b9060 Use-After-Free RCE via llama-server
CVE-2026-43631
9.2 Critical
-
ggml llama.cpp
llama.cpp b4882-b8487 Out-of-Bounds Read Information Disclosure
CVE-2026-43630
Fix available
6.3 Medium
-
ggml llama.cpp
llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore
CVE-2026-43629
9.2 Critical
-
ggml llama.cpp
llama.cpp b3978–b9058 Integer Underflow via DRY Sampler
CVE-2026-43628
8.5 High
-
ggml llama.cpp
llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function
CVE-2026-43627
8.5 High
-
ggml llama.cpp
llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp
CVE-2026-70640
Fix available
7.3 High
-
ggml llama.cpp
llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp
CVE-2026-70639
Fix available
6.8 Medium
-
ggml llama.cpp
llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp
CVE-2026-70638
Fix available
8.5 High
-
ggml llama.cpp
llama.cpp b1886–b7445 Double Free via llama-android.cpp
CVE-2026-43622
Fix available
8.5 High
-
ggml llama.cpp
llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend
CVE-2026-34159
Public exploitFix available
9.8 Critical
-
ggml llama.cpp
llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing
CVE-2026-33298
Fix available
7.8 High
-
ggml llama.cpp
llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix
CVE-2026-27940
Public exploitFix available
7.8 High
-
ggml llama.cpp
llama.cpp has Out-of-bounds Write in llama-server
CVE-2026-21869
Fix available
8.8 High
-
ggml llama.cpp
llama.cpp tokenizer signed vs. unsigned heap overflow
CVE-2025-52566
Fix available
8.6 High
-
ggml llama.cpp
llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model
CVE-2025-49847
Fix available
8.8 High
-
ggerganov llama.cpp
llama.cpp allows write-what-where in rpc_server::set_tensor
CVE-2024-42479
10.0 Critical
-
ggerganov llama.cpp
llama.cpp allows Arbitrary Address Read in rpc_server::get_tensor
CVE-2024-42478
5.3 Medium
-
ggerganov llama.cpp
llama.cpp global-buffer-overflow in ggml_type_size
CVE-2024-42477
5.3 Medium
-
ggerganov llama.cpp
llama.cpp null pointer dereference in gguf_init_from_file
CVE-2024-41130
5.4 Medium
-
ggerganov llama.cpp
Use of Uninitialized Variable Vulnerability in llama.cpp
CVE-2024-32878
7.1 High
-
ggerganov llama.cpp
A heap-based buffer overflow vulnerability exists in the GGUF library GGUF_TYPE_ARRAY...
CVE-2024-21825
8.8 High
-
ggerganov llama.cpp
A heap-based buffer overflow vulnerability exists in the GGUF library gguf_fread_str...
CVE-2024-23496
8.8 High
-
ggerganov llama.cpp
A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors...
CVE-2024-21836
8.8 High
-
ggml llama.cpp
A heap-based buffer overflow vulnerability exists in the GGUF library info->ne functionality...
CVE-2024-21802
8.8 High
-
ggerganov llama.cpp
A heap-based buffer overflow vulnerability exists in the GGUF library header.n_kv functionality...
CVE-2024-23605
8.8 High