Every public CVE, as it is published
The whole CVE List, enriched with NVD scores, CISA's known exploited catalog and EPSS exploit probabilities. Updated every few minutes; last read 10 min ago.
At a glance
Published CVEs; rejected ones are not counted.
- 410,659All CVEsplus 19,189 rejected
- 898Last 24 hours4,250 in the last 7 days
- 16,600Last 30 days1,522 of them critical
- 1,786Known exploitedin the CISA KEV catalog
CVEs published per year
All time, by publication date in UTC; follows the filter above.
- Critical
- High
- Medium
- Low
- Not scored
Show the numbers as a table
| Period | Critical | High | Medium | Low | Not scored | Total | Cumulative |
|---|---|---|---|---|---|---|---|
| 2026 | 6 | 12 | 18 | 1 | 0 | 37 | 41 |
| 2025 | 0 | 3 | 1 | 0 | 0 | 4 | 4 |
| Title | ||
|---|---|---|
| CVE-2026-133710 | llama.cpp b11003 before b12556 Heap Out-of-Bounds Write via hrm_text Model Loaderggml-org · llama.cpp | High8.5 |
| CVE-2026-119052 | llama.cpp b2877 before b11935 ggml-rpc Server DoS via Oversized recv_msg Lengthggml-org · llama.cpp | High8.7 |
| CVE-2026-118375 | llama.cpp b8841 before b11865 Stack-based Buffer Overflow via ggml-rpc RDMA rdma_recv()ggml-org · llama.cpp | Critical9.2 |
| CVE-2026-116840 | llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_readerggml-org · llama.cpp | Medium6.9 |
| CVE-2026-116829 | llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_readerPublic exploitggml-org · llama.cpp | Medium6.9 |
| CVE-2026-116816 | llama.cpp b5899 before b10261 Heap Out-of-Bounds Write via plamo2 Tokenizerggml-org · llama.cpp | High8.5 |
| CVE-2025-71439 | llama.cpp before b5649 Heap Out-of-Bounds Read via llama_vocab::impl::print_infoPublic exploitggml-org · llama.cpp | Medium6.8 |
| CVE-2024-58400 | llama.cpp before b3701 Out-of-Bounds Read in llama_decode via Token IDsggml-org · llama.cpp | High8.8 |
| CVE-2024-58399 | llama.cpp before b2731 Out-of-Bounds Read via GGUF Tensor Offsetsggml-org · llama.cpp | Medium6.9 |
| CVE-2026-116467 | ggml-org llama.cpp Mirostat Sampler llama-sampler.cpp assertionggml-org · llama.cpp | Medium6.9 |
| CVE-2026-116096 | ggml-org llama.cpp Pocket-TTS pockettts-gen.cpp list_pockettts_state_slots out-of-bounds writePublic exploitggml-org · llama.cpp | Medium4.8 |
| CVE-2026-110810 | ggml-org whisper.cpp Model Loader whisper_model_load out-of-boundsPublic exploitggml-org · whisper.cpp | Low2.4 |
| CVE-2026-107183 | llama.cpp before b11393 Use-After-Free via common_chat_peg_mapper chat_parserggml-org · llama.cpp | Critical9.2 |
| CVE-2026-86317 | ggml-org llama.cpp RPC Server ggml-rpc.cpp deserialize_tensor assertionggml-org · llama.cpp | Medium6.9 |
| CVE-2026-78148 | ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp graph_compute null pointer dereferenceggml-org · llama.cpp | Medium6.9 |
| CVE-2026-78147 | ggml-org llama.cpp ggml-RPC Server ggml-rpc.cpp deserialize_tensor deserializationggml-org · llama.cpp | Medium6.9 |
| CVE-2026-43632 | llama.cpp b7492–b9060 Use-After-Free in Tokenization Endpointsggml-org · llama.cpp | Critical9.2 |
| CVE-2026-43631 | llama.cpp b7492–b9060 Use-After-Free RCE via llama-serverggml-org · llama.cpp | Critical9.2 |
| CVE-2026-43630 | llama.cpp b4882-b8487 Out-of-Bounds Read Information Disclosureggml-org · llama.cpp | Medium6.3 |
| CVE-2026-43629 | llama.cpp b4882–b9058 Buffer Overflow in KV Cache State Restoreggml-org · llama.cpp | Critical9.2 |
| CVE-2026-43628 | llama.cpp b3978–b9058 Integer Underflow via DRY Samplerggml-org · llama.cpp | High8.5 |
| CVE-2026-43627 | llama.cpp b1283–b9058 Integer Overflow in llama_batch_init() Functionggml-org · llama.cpp | High8.5 |
| CVE-2026-70640 | llama.cpp b1886–b7445 Race Condition Use-After-Free via llama-android.cppggml-org · llama.cpp | High7.3 |
| CVE-2026-70639 | llama.cpp b1886–b7445 Null Pointer Dereference DoS via llama-android.cppggml-org · llama.cpp | Medium6.8 |
| CVE-2026-70638 | llama.cpp b1886–b7445 Integer Overflow via new_1batch() in llama-android.cppggml-org · llama.cpp | High8.5 |
| CVE-2026-43622 | llama.cpp b1886–b7445 Double Free via llama-android.cppggml-org · llama.cpp | High8.5 |
| CVE-2026-18581 | ggml-org llama.cpp Jinja Minja Template parser.cpp assertionPublic exploitggml-org · llama.cpp | Medium4.8 |
| CVE-2026-17513 | ggml-org whisper.cpp ggml.c ggml_ftype_to_ggml_type assertionPublic exploitggml-org · whisper.cpp | Medium4.8 |
| CVE-2026-17512 | ggml-org whisper.cpp log_mel_spectrogram out-of-boundsggml-org · whisper.cpp | Medium4.8 |
| CVE-2026-17501 | ggml-org llama.cpp JSON-Schema-to-GBNF Conversion json-schema-to-grammar.cpp transform recursionggml-org · llama.cpp | Medium6.9 |
| CVE-2026-17500 | ggml-org llama.cpp json-schema-to-grammar.cpp _visit_pattern null pointer dereferenceggml-org · llama.cpp | Medium6.9 |
| CVE-2026-10298 | ggml-org whisper.cpp ggml.c whisper_model_load null pointer dereferencePublic exploitggml-org · whisper.cpp | Medium4.8 |
| CVE-2026-34159 | llama.cpp: Unauthenticated RCE via GRAPH_COMPUTE buffer=0 bypass in llama.cpp RPC backendPublic exploitggml-org · llama.cpp | Critical9.8 |
| CVE-2026-33298 | llama.cpp has a Heap Buffer Overflow via Integer Overflow in GGUF Tensor ParsingPublic exploitggml-org · llama.cpp | High7.8 |
| CVE-2026-27940 | llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 FixPublic exploitggml-org · llama.cpp | High7.8 |
| CVE-2026-2069 | ggml-org llama.cpp GBNF Grammar llama-grammar.cpp llama_grammar_advance_stack stack-based overflowPublic exploitggml-org · llama.cpp | Medium4.8 |
| CVE-2026-21869 | llama.cpp has Out-of-bounds Write in llama-serverPublic exploitggml-org · llama.cpp | High8.8 |
| CVE-2025-14569 | ggml-org whisper.cpp common-whisper.cpp read_audio_data use after freePublic exploitggml-org · whisper.cpp | Medium4.8 |
| CVE-2025-53630 | Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in ggufPublic exploitggml-org · llama.cpp | High8.9 |
| CVE-2025-52566 | llama.cpp tokenizer signed vs. unsigned heap overflowPublic exploitggml-org · llama.cpp | High8.6 |
| CVE-2025-49847 | llama.cpp Vulnerable to Buffer Overflow via Malicious GGUF ModelPublic exploitggml-org · llama.cpp | High8.8 |