| High | llama.cpp through commit 97f06e9, when started with the --reranking flag, allows remote attackers to cause a denial of service (std::badalloc and HTTP 500) via a negative topn value in a POST request to /rerank.CVE-2026-52132 | 2026-09-01 | See advisory |
| High | llama.cpp b5693 and before has a Reachable Assertion via the gguf_reader::read function.CVE-2026-52131 | 2026-09-01 | See advisory |
| High | llama.cpp b5693 and before is vulnerable to Uncontrolled Recursion in common/json-schema-to-grammar.cpp, resulting in a denial of service.CVE-2026-52130 | 2026-09-01 | See advisory |
| High | llama.cpp builds b1886 through b7445 contain a race condition use-after-free vulnerability in the LLaMA-Android JNI wrapper where bench1model() and free1context() lack synchronization, allowing Thread A to operate on freed memory while…CVE-2026-70640 | 2026-08-06 | See advisory |
| Medium | 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.CVE-2026-70639 | 2026-08-06 | See advisory |
| High | llama.cpp builds b1886 through b7445 contain an integer overflow vulnerability in the LLaMA-Android JNI wrapper where the new1batch() function multiplies sizeof(llamaseqid) by an attacker-controlled nseqmax parameter without overflow…CVE-2026-70638 | 2026-08-06 | See advisory |
| Critical | llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank, and /anthropic/counttokens) that…CVE-2026-43632 | 2026-08-06 | See advisory |
| Critical | llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated remote attackers to execute arbitrary…CVE-2026-43631 | 2026-08-06 | See advisory |
| Medium | llama.cpp builds b4882 before b8487 contain an out-of-bounds read vulnerability in the recurrent memory state restore path that allows attackers with write access to the slot save directory to read memory past the end of the allocated…CVE-2026-43630 | 2026-08-06 | See advisory |
| Critical | llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the statereaddata() function computes write size without overflow checking, allowing attackers with write access to…CVE-2026-43629 | 2026-08-06 | See advisory |
| High | llama.cpp builds b3978 through b9058 contain an integer underflow and out-of-bounds read vulnerability in the DRY sampler that allows unauthenticated attackers to trigger a heap buffer underflow by sending a crafted HTTP request with…CVE-2026-43628 | 2026-08-06 | See advisory |
| High | llama.cpp builds b1283 through b9058 contain an integer overflow vulnerability in the llamabatchinit() function where unchecked multiplications in malloc() calls can wrap past INT32_MAX when computing allocation sizes.CVE-2026-43627 | 2026-08-06 | See advisory |
| High | llama.cpp builds b1886 through b7445 contain a double free vulnerability in the LLaMA-Android JNI wrapper where new1batch() allocates memory using malloc() while free1batch() deallocates it using the C++ delete operator, causing heap…CVE-2026-43622 | 2026-08-06 | See advisory |
| Critical | llama.cpp is an inference of several LLM models in C/C++.CVE-2026-34159 · GHSA-j8rj-fmpv-wcxw | 2026-04-01 | b8492 |
| High | llama.cpp is an inference of several LLM models in C/C++.CVE-2026-33298 · GHSA-96jg-mvhq-q7q7 | 2026-03-24 | b7824 |
| High | llama.cpp is an inference of several LLM models in C/C++.CVE-2026-27940 · GHSA-3p4r-fq3f-q74v | 2026-03-12 | b8146 |
| High | llama.cpp is an inference of several LLM models in C/C++.CVE-2026-21869 · GHSA-8947-pfff-2f3c | 2026-01-08 | See advisory |
| High | Integer Overflow in GGUF Parser can lead to Heap Out-of-Bounds Read/Write in ggufCVE-2025-53630 · GHSA-vgg9-87g3-85w8 | 2025-07-10 | See advisory |
| Medium | Heap-based Buffer Over-read in llamamodelloadGHSA-g4cc-763q-h9h6 | 2025-06-25 | See advisory |
| High | llama.cpp is an inference of several LLM models in C/C++.CVE-2025-52566 · GHSA-7rxv-5jhh-j6xx | 2025-06-24 | b5721 |
| High | llama.cpp is an inference of several LLM models in C/C++.CVE-2025-49847 · GHSA-8wwf-w4qm-gpqr | 2025-06-17 | b5662 |
| Critical | llama.cpp provides LLM inference in C/C++.CVE-2024-42479 · GHSA-wcr5-566p-9cwj | 2024-08-12 | b3561 |
| Medium | llama.cpp provides LLM inference in C/C++.CVE-2024-42478 · GHSA-5vm9-p64x-gqw9 | 2024-08-12 | b3561 |
| Medium | llama.cpp provides LLM inference in C/C++.CVE-2024-42477 · GHSA-mqp6-7pv6-fqjf | 2024-08-12 | b3561 |
| Medium | llama.cpp provides LLM inference in C/C++.CVE-2024-41130 · GHSA-49q7-2jmh-92fp | 2024-07-22 | b3427 |
| High | Llama.cpp is LLM inference in C/C++.CVE-2024-32878 · GHSA-p5mv-gjc5-mwqv | 2024-04-26 | b2740 |
| High | A heap-based buffer overflow vulnerability exists in the GGUF library header.n_kv functionality of llama.cpp Commit 18c2e17.CVE-2024-23605 | 2024-02-26 | 2024-01-09 |
| High | A heap-based buffer overflow vulnerability exists in the GGUF library gguffreadstr functionality of llama.cpp Commit 18c2e17.CVE-2024-23496 | 2024-02-26 | 2024-01-09 |
| High | A heap-based buffer overflow vulnerability exists in the GGUF library header.n_tensors functionality of llama.cpp Commit 18c2e17.CVE-2024-21836 | 2024-02-26 | 2024-01-09 |
| High | A heap-based buffer overflow vulnerability exists in the GGUF library GGUFTYPEARRAY/GGUFTYPESTRING parsing functionality of llama.cpp Commit 18c2e17.CVE-2024-21825 | 2024-02-26 | 2024-01-09 |
| High | A heap-based buffer overflow vulnerability exists in the GGUF library info->ne functionality of llama.cpp Commit 18c2e17.CVE-2024-21802 | 2024-02-26 | 2024-01-09 |