Medium severity6.1NVD Advisory· Published Oct 27, 2026
CVE-2026-116840
CVE-2026-116840
Description
llama.cpp b5854 before b11275 contains an integer overflow vulnerability in gguf_init_from_reader that bypasses the CVE-2025-53630 size check when padding near-SIZE_MAX tensor sizes. Attackers can supply a crafted GGUF file whose tensor size pads to zero, causing an undersized data blob and out-of-bounds reads by consumers.
Affected products
1Patches
Vulnerability mechanics
References
6- github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cppnvd
- github.com/ggml-org/llama.cpp/commit/a6ea155d3d38b3f6f43d0c0dc29c2d592413ef44nvd
- github.com/ggml-org/llama.cpp/issues/26978nvd
- github.com/ggml-org/llama.cpp/pull/26979nvd
- github.com/ggml-org/llama.cpp/releases/tag/b11275nvd
- www.vulncheck.com/advisories/llama-cpp-b5854-before-b11275-integer-overflow-in-gguf-init-from-readernvd
News mentions
0No linked articles in our index yet.