{"id":"CVE-2024-58399","published":"2026-10-27T01:19:02.810","lastModified":"2026-10-27T01:19:02.810","description":"llama.cpp before b2731 contains an out-of-bounds read vulnerability in llama_model_loader that allows attackers to read memory outside the mapped model file via crafted GGUF tensor offsets. Attackers can supply a crafted or truncated GGUF model file with arbitrary 64-bit tensor offsets to crash the process or load adjacent process memory as model weights.","cvssScore":6.1,"cvssSeverity":"MEDIUM","cvssVector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H","cwes":["CWE-125"],"vendors":[],"products":[],"references":[{"url":"https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/issues/6774","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/pull/6885","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/releases/tag/b2731","tags":[]},{"url":"https://www.vulncheck.com/advisories/llama-cpp-before-b2731-out-of-bounds-read-via-gguf-tensor-offsets","tags":[]}],"exploitRefs":[{"url":"https://github.com/ggml-org/llama.cpp/blob/b2730/llama.cpp#L3002-L3004","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/commit/0ead1f1072fdc70720f92e008a294dc74a826b1d","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/issues/6774","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/pull/6885","tags":[]},{"url":"https://github.com/ggml-org/llama.cpp/releases/tag/b2731","tags":[]}],"hasPoc":true,"ai":null}