CVE-2026-116829
mediumllama.cpp b10398 before b11301 contains an integer overflow vulnerability in gguf_init_from_reader that allows attackers to bypass tensor element-count validat…
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.
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:L/A:H Affected products
Not reported by the source (unknown — not "none").
Weakness classification (CWE)
Source: NVD / CISA. “NVD-CWE-Other” and “NVD-CWE-noinfo” mean NVD could not assign a specific weakness.
Mitigation & advisories
No vendor advisory or patch reference tagged by NVD. Check the references below.
References
- https://github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L701 disclosure@vulncheck.com
- https://github.com/ggml-org/llama.cpp/commit/2149c00f4442dc59302e134a02e4c99d5f7ed9fc disclosure@vulncheck.com
- https://github.com/ggml-org/llama.cpp/issues/29383 disclosure@vulncheck.com
- https://github.com/ggml-org/llama.cpp/pull/29384 disclosure@vulncheck.com
- https://github.com/ggml-org/llama.cpp/releases/tag/b11301 disclosure@vulncheck.com
- https://www.vulncheck.com/advisories/llama-cpp-b10398-before-b11301-integer-overflow-in-gg... disclosure@vulncheck.com