CVE-2026-116829
llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader
ggml-org llama.cpp
CVSS
6.9MediumExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV
Exploit odds (EPSS)No scoreNo FIRST EPSS score in this snapshot yet
What fixes it
- 0.6.0llama.cppCVE List
A fixed version on one release line is not the upgrade target for every line. Check your exact version and any vendor backports.
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.
Text from CVE List
Affected versions 2
- llama.cppaffected: b10398 before b11301CVE List
- llama.cppaffected: 0.1.0 before 0.6.0CVE List
References 6
- github.com/ggml-org/llama.cpp/pull/29384Fixvia CVE List
- github.com/ggml-org/llama.cpp/commit/2149c00f4442dc59302e134a02e4c99d5f7ed9fcFixvia CVE List
- github.com/ggml-org/llama.cpp/releases/tag/b11301Fixvia CVE List
- vulncheck.com/advisories/llama-cpp-b10398-before-b11301-integer-overflow-in-gguf-init-from-readerAdvisoryvia CVE List
- github.com/ggml-org/llama.cpp/issues/29383Referencevia CVE List
- github.com/ggml-org/llama.cpp/blob/v0.5.0/ggml/src/gguf.cpp#L701Referencevia CVE List