6.6
MediumCVSS 3.1 · from VulnCheck
CVE-2026-116829
llama.cpp b10398 before b11301 Integer Overflow in gguf_init_from_reader
llama.cpp · Integer overflow · CWE-190Affectedllama.cpp
FixUpdate to 0.6.0 or newer
PublishedOct 27, 00:33 · VulnCheck
ScoredOct 27 · 6.6 · VulnCheck
Exploit code publicNone known · checked 21:18 UTC
ExploitedNone known · CISA KEV checked 22:10 UTC
What we know
No known exploitation. CISA KEV, checked 22:10 UTC.
No public exploit code known. Exploit-DB, Metasploit, Nuclei, checked 21:18 UTC.
An attacker needs local access to the machine. CVSS: local.
Someone has to open, click or run something first. CVSS: user interaction required.
A successful attack can take the service down. CVSS impact.
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.
From VulnCheck
Affected and fixed versions
ProductAffectedFixed inllama.cppb10398 – before b11301–llama.cpp0.1.0 – before 0.6.00.6.0
Exploit code
Exploit-DBnone knownMetasploitnone knownNucleinone known