- CVSS
- MEDIUM · 6.1v3.1CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H
- Published
- 2026-10-27
- Weakness
- CWE-190
- Source
- nvd.nist.gov/vuln/detail/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.
References
- https://github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L794-L795
- https://github.com/ggml-org/llama.cpp/commit/a6ea155d3d38b3f6f43d0c0dc29c2d592413ef44
- https://github.com/ggml-org/llama.cpp/issues/26978
- https://github.com/ggml-org/llama.cpp/pull/26979
- https://github.com/ggml-org/llama.cpp/releases/tag/b11275
- https://www.vulncheck.com/advisories/llama-cpp-b5854-before-b11275-integer-overflow-in-gguf-init-from-reader
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-116840 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.