CVE-2026-133710
Awaiting Analysis Awaiting Analysis - Queue

Integer Overflow in llama.cpp GGUF Model Loader

Vulnerability report for CVE-2026-133710, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.

Publication date: 2026-11-20

Last updated on: 2026-11-20

Assigner: VulnCheck

Description

llama.cpp b11003 before b12556 contains an integer overflow in the hrm_text loader load_arch_hparams() that allows attackers to bypass the block count check using crafted GGUF metadata. Attackers can supply a GGUF model whose layer factors wrap modulo 2^32, causing load_arch_tensors() to write tensor pointers past model.layers, corrupting heap memory and potentially enabling code execution.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-11-20
Last Modified
2026-11-20
Generated
2026-11-20
AI Q&A
2026-11-20
EPSS Evaluated
N/A
NVD
EUVD

Affected Vendors & Products

Currently, no data is known.

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-190 The product performs a calculation that can produce an integer overflow or wraparound when the logic assumes that the resulting value will always be larger than the original value. This occurs when an integer value is incremented to a value that is too large to store in the associated representation. When this occurs, the value may become a very small or negative number.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

llama.cpp versions before b12556 have an integer overflow in the hrm_text loader's load_arch_hparams() function. Attackers can exploit this by crafting GGUF metadata with layer factors that wrap around modulo 2^32. This bypasses block count checks and causes load_arch_tensors() to write tensor pointers beyond the allocated model.layers array, leading to heap memory corruption and potential code execution.

Impact Analysis

If exploited, this vulnerability could allow attackers to execute arbitrary code on your system. Since it involves heap memory corruption, it may crash applications or enable full system compromise depending on the context in which llama.cpp is used.

Mitigation Strategies

Update llama.cpp to version b12556 or later to address the integer overflow in hrm_text loader load_arch_hparams().

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-133710. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart

Security Radar

News mentioning this vulnerability
Loading related security news...