Vulnerability Description
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 Score
MEDIUM
Related Weaknesses (CWE)
References
- https://github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L701
- https://github.com/ggml-org/llama.cpp/commit/2149c00f4442dc59302e134a02e4c99d5f7
- https://github.com/ggml-org/llama.cpp/issues/29383
- https://github.com/ggml-org/llama.cpp/pull/29384
- https://github.com/ggml-org/llama.cpp/releases/tag/b11301
- https://www.vulncheck.com/advisories/llama-cpp-b10398-before-b11301-integer-over
FAQ
What is CVE-2026-116829?
CVE-2026-116829 is a vulnerability with a CVSS score of 6.6 (MEDIUM). 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 wra...
How severe is CVE-2026-116829?
CVE-2026-116829 has been rated MEDIUM with a CVSS base score of 6.6/10. Review the CVSS metrics above for detailed severity breakdown.
Is there a patch for CVE-2026-116829?
Check the references section above for vendor advisories and patch information. Review vendor security bulletins for remediation guidance.