6.6Media
CVE-2026-116829llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader
Descripción
llama.cpp b10398 before b11301 contains an integer overflow vulnerability in gguf_init_from_reader that allows attackers to bypass tensor element-count validation by supplying shapes whose product wraps to zero. Attackers can craft GGUF files with enormous tensor extents that overflow ggml_nbytes() and strides, causing out-of-bounds memory access when buffers are sized from wrapped byte counts.
Debilidad (CWE):
CWE-190
Datos: CVE.org, NVD, CISA KEV, FIRST EPSS, Ubuntu. Se publican tal como los indican las fuentes, en inglés.
Productos y versiones afectados
Referencias y parches
- https://github.com/ggml-org/llama.cpp/issues/29383 issue-tracking
- https://github.com/ggml-org/llama.cpp/pull/29384 patchissue-tracking
- https://github.com/ggml-org/llama.cpp/commit/2149c00f4442dc59302e134a02e4c99d5f7ed9fc patch
- https://github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L701 technical-description
- llama.cpp b11301 Release Notes release-notes
- VulnCheck Advisory: llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader third-party-advisory