ggml-org llama.cpp

• CVE-2026-119052 High 7.5 llama.cpp b2877 before b11935 ggml-rpc Server DoS via Oversized recv_msg Length 0.6%
• CVE-2026-118375 High 8.1 llama.cpp b8841 before b11865 Stack-based Buffer Overflow via ggml-rpc RDMA rdma_recv() 0.4%
• CVE-2026-116840 Medium 6.1 llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader 0.1%
• CVE-2026-116829 Medium 6.6 llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader 0.1%
• CVE-2026-116816 High 7.8 llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizer 0.1%
• CVE-2025-71439 Medium 5.5 llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_info 0.1%
• CVE-2024-58400 High 8.2 llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDs 0.4%
• CVE-2024-58399 Medium 6.1 llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsets 0.1%
• CVE-2026-116467 Medium 5.3 ggml-org llama.cpp Mirostat Sampler llama-sampler.cpp assertion 0.6%
• CVE-2026-116096 Medium 5.3 ggml-org llama.cpp Pocket-TTS pockettts-gen.cpp list_pockettts_state_slots out-of-bounds write 0.1%
• CVE-2026-107183 High 8.1 llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parser 0.4%
• CVE-2026-86317 Medium 5.3 ggml-org llama.cpp RPC Server ggml-rpc.cpp deserialize_tensor assertion 0.7%
• CVE-2026-78148 Medium 5.3 ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp graph_compute null pointer dereference 0.7%
• CVE-2026-78147 High 7.3 ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp deserialize_tensor deserialization 0.6%
• CVE-2026-43632 High 8.1 llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpoints 0.5%
• CVE-2026-43631 High 8.1 llama.cpp b7492–b9060 Use-After-Free RCE via llama-server 0.6%
• CVE-2026-43630 Medium 6.5 llama.cpp b4882-b8487 Out-of-Bounds Read Information Disclosure 0.5%
• CVE-2026-43629 High 8.1 llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restore 0.7%
• CVE-2026-43628 High 7.8 llama.cpp b3978–b9058 Integer Underflow via DRY Sampler 0.2%
• CVE-2026-43627 High 7.8 llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Function 0.2%
• CVE-2026-70640 High 7.0 llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cpp 0.2%
• CVE-2026-70639 Medium 5.5 llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cpp 0.2%
• CVE-2026-70638 High 7.8 llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cpp 0.2%
• CVE-2026-43622 High 7.8 llama.cpp b1886–b7445 Double Free via llama-android.cpp 0.2%
• CVE-2026-18581 Low 3.3 ggml-org llama.cpp Jinja Minja Template parser.cpp assertion 0.2%
• CVE-2026-17501 Medium 5.3 ggml-org llama.cpp JSON-Schema-to-GBNF Conversion json-schema-to-grammar.cpp transform recursion 0.7%
• CVE-2026-17500 Medium 5.3 ggml-org llama.cpp json-schema-to-grammar.cpp _visit_pattern null pointer dereference 0.7%
• CVE-2026-34159 Critical 9.8 llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backend 1.6%
• CVE-2026-33298 High 7.8 llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor Parsing 0.5%
• CVE-2026-27940 High 7.8 llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix 0.2%
• CVE-2026-2069 Low 3.3 ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflow 0.1%
• CVE-2026-21869 High 8.8 llama.cpp has Out-of-bounds Write in llama-server 0.5%
• CVE-2025-53630 High 8.9 Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in gguf 0.4%
• CVE-2025-52566 High 8.6 llama.cpp tokenizer signed vs. unsigned heap overflow 0.4%
• CVE-2025-49847 High 8.8 llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF Model 0.5%