CVE-2026-116840

llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader

Published Oct 27, 2026 CVSS 4.0 · 6.9 Medium EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

An integer overflow in the gguf_init_from_reader function allows an attacker to craft a GGUF file whose padded tensor size is reduced to zero, subverting the size check that protects against overly large tensors. When the consumer subsequently reads the undersized data blob, it performs out-of-bounds reads that may expose memory contents beyond the intended buffer. This flaw is specific to ggml-org’s llama.cpp implementation and can be exploited when a malicious model file is supplied to a running instance.

Affected Systems

The vulnerability affects the llama.cpp project maintained by ggml-org, specifically all releases from commit b5854 up through, but excluding, commit b11275. Users running any version of llama.cpp before commit b11275 are susceptible.

Risk and Exploitability

The CVSS score of 6.9 indicates moderate severity. EPSS is not available, so the likelihood of exploitation in the wild cannot be quantified at this time; however, the vulnerability is not listed in the CISA KEV catalog, suggesting no known widespread exploitation. Attackers must provide a crafted GGUF file to the consumer, which could be done locally or over network interfaces that ingest model files. Successful exploitation leads to out-of-bounds reads that may leak sensitive data or be leveraged for further attacks.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade llama.cpp to version b11275 or later, which removes the padding overflow problem
  • Implement runtime validation that verifies the computed tensor size is non‑zero and within expected limits before reading the file data
  • Limit the source of GGUF model files to trusted repositories and perform hash or integrity checks to avoid loading tampered files

Generated by OpenCVE AI on October 27, 2026 at 08:40 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'none', 'Technical Impact': 'partial'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Ggml-org
Ggml-org llama.cpp
Vendors & Products Ggml-org
Ggml-org llama.cpp
Type Values Removed Values Added
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.
Title llama.cpp b5854 before b11275 Integer Overflow in gguf_init_from_reader
First Time appeared Ggml
Ggml llama.cpp
Weaknesses CWE-190
CPEs cpe:2.3:a:ggml:llama.cpp:*:*:*:*:*:*:*:*
Vendors & Products Ggml
Ggml llama.cpp
References
Metrics cvssV3_1

{'score': 6.1, 'vector': 'CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:L/I:N/A:H'}

cvssV4_0

{'score': 6.9, 'vector': 'CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:L/VI:N/VA:H/SC:N/SI:N/SA:N'}

Weaknesses
  • CWE-190

    Integer Overflow or Wraparound

Sources

Status
PUBLISHED
Assigner
VulnCheck
Published
Updated
Oct 27, 2026, 2:14 PM
Reserved
Oct 27, 2026, 12:10 AM
Status
Awaiting Analysis
Published
Oct 27, 2026, 1:19 AM
Modified
Oct 27, 2026, 3:59 PM