{"resultsPerPage":1,"startIndex":0,"totalResults":1,"format":"NVD_CVE","version":"2.0","timestamp":"2026-05-05T02:09:57.883","vulnerabilities":[{"cve":{"id":"CVE-2025-49847","sourceIdentifier":"security-advisories@github.com","published":"2025-06-17T20:15:32.437","lastModified":"2025-08-27T13:48:14.223","vulnStatus":"Analyzed","cveTags":[],"descriptions":[{"lang":"en","value":"llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Specifically, the helper _try_copy in llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() casts a very large size_t token length into an int32_t, causing the length check (if (length < (int32_t)size)) to be bypassed. As a result, memcpy is still called with that oversized size, letting a malicious model overwrite memory beyond the intended buffer. This can lead to arbitrary memory corruption and potential code execution. This issue has been patched in version b5662."},{"lang":"es","value":"llama.cpp es una inferencia de varios modelos LLM en C/C++. Antes de la versión b5662, un vocabulario de modelo GGUF proporcionado por un atacante podía provocar un desbordamiento de búfer en el código de carga de vocabulario de llama.cpp. Específicamente, el asistente _try_copy en llama.cpp/src/vocab.cpp: llama_vocab::impl::token_to_piece() convierte una longitud de token size_t muy grande en un int32_t, lo que provoca que se omita la comprobación de longitud (si (length &lt; (int32_t)size)). Como resultado, se sigue llamando a memcpy con ese tamaño excesivo, lo que permite que un modelo malicioso sobrescriba la memoria más allá del búfer previsto. Esto puede provocar corrupción de memoria arbitraria y la posible ejecución de código. Este problema se ha corregido en la versión b5662."}],"metrics":{"cvssMetricV31":[{"source":"security-advisories@github.com","type":"Secondary","cvssData":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","baseScore":8.8,"baseSeverity":"HIGH","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"NONE","userInteraction":"REQUIRED","scope":"UNCHANGED","confidentialityImpact":"HIGH","integrityImpact":"HIGH","availabilityImpact":"HIGH"},"exploitabilityScore":2.8,"impactScore":5.9}]},"weaknesses":[{"source":"security-advisories@github.com","type":"Secondary","description":[{"lang":"en","value":"CWE-119"},{"lang":"en","value":"CWE-195"}]}],"configurations":[{"nodes":[{"operator":"OR","negate":false,"cpeMatch":[{"vulnerable":true,"criteria":"cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*","versionEndExcluding":"b5662","matchCriteriaId":"CD259F6A-4B43-4B07-83A5-544F900CD023"}]}]}],"references":[{"url":"https://github.com/ggml-org/llama.cpp/commit/3cfbbdb44e08fd19429fed6cc85b982a91f0efd5","source":"security-advisories@github.com","tags":["Patch"]},{"url":"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-8wwf-w4qm-gpqr","source":"security-advisories@github.com","tags":["Mitigation","Vendor Advisory"]}]}}]}