{"id":"CVE-2026-133710","aliases":[],"url":"https://o3.security/vulnerability/CVE-2026-133710","summary":"llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata.…","details":"llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.","published":"2026-11-20T13:18:47.340","modified":"2026-11-20T13:18:47.467","cvss":{"score":7.8,"severity":"HIGH","vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H"},"epss":null,"cisaKev":null,"exploitsKnown":null,"affectedPackages":[],"fix":{"url":"https://github.com/ggml-org/llama.cpp/commit/50518b64c6f2191a116d2760042f106c4b3387d7","label":"ggml-org/llama.cpp@50518b6"},"references":[{"type":"WEB","url":"https://github.com/ggml-org/llama.cpp/blob/b12555/src/models/hrm-text.cpp"},{"type":"WEB","url":"https://github.com/ggml-org/llama.cpp/commit/50518b64c6f2191a116d2760042f106c4b3387d7"},{"type":"WEB","url":"https://github.com/ggml-org/llama.cpp/pull/32601"},{"type":"WEB","url":"https://github.com/ggml-org/llama.cpp/releases/tag/b12556"},{"type":"WEB","url":"https://www.vulncheck.com/advisories/llama-cpp-b11003-before-b12556-heap-out-of-bounds-write-via-hrm-text-model-loader"}],"provenance":{"sources":["OSV.dev","NVD","FIRST.org (EPSS)"],"lastVerified":"2026-11-20T13:18:47.467"}}