https://cve.radiocsirt.org Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Tue, 06 Oct 2026 09:09:18 +0000 https://cve.radiocsirt.org/vuln/euvd-2026-245797 EUVD-2026-245797 https://cve.radiocsirt.org/vuln/euvd-2026-245797 https://cve.radiocsirt.org/vuln/fkie_cve-2025-52566 <p>llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp&#39;s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.</p> <p>llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp&#39;s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.</p> https://cve.radiocsirt.org/vuln/fkie_cve-2025-52566 https://cve.radiocsirt.org/vuln/oesa-2025-2371 <p><strong>Affected:</strong> openEuler:24.03-LTS-SP1: llama.cpp</p> <p>Security Fix(es):</p> <p>llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp&amp;apos;s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.(CVE-2025-52566)</p> <p><strong>Affected:</strong> openEuler:24.03-LTS-SP1: llama.cpp</p> <p>Security Fix(es):</p> <p>llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp&amp;apos;s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.(CVE-2025-52566)</p> https://cve.radiocsirt.org/vuln/oesa-2025-2371 https://cve.radiocsirt.org/vuln/ubuntu-cve-2025-52566 <p><strong>Affected:</strong> Ubuntu:25.10: llama.cpp, Ubuntu:26.04:LTS: llama.cpp</p> <p>llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp&#39;s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.</p> <p><strong>Affected:</strong> Ubuntu:25.10: llama.cpp, Ubuntu:26.04:LTS: llama.cpp</p> <p>llama.cpp is an inference of several LLM models in C/C++. Prior to version b5721, there is a signed vs. unsigned integer overflow in llama.cpp&#39;s tokenizer implementation (llama_vocab::tokenize) (src/llama-vocab.cpp:3036) resulting in unintended behavior in tokens copying size comparison. Allowing heap-overflowing llama.cpp inferencing engine with carefully manipulated text input during tokenization process. This issue has been patched in version b5721.</p> https://cve.radiocsirt.org/vuln/ubuntu-cve-2025-52566