CVE-2025-66960

Description

A flaw was found in ollama. A remote attacker can exploit this vulnerability by providing untrusted GGUF (GGML Unified Format) metadata with a specially crafted string length. This can cause the readGGUFV1String function to improperly process the input, leading to a denial of service, which makes the service unavailable to legitimate users.

Statement

This vulnerability is rated Moderate for Red Hat products. An issue in ollama allows a remote attacker to cause a denial of service by providing untrusted GGUF metadata. This affects Red Hat Ansible Automation Platform versions 2.4, 2.5, and 2.6, as well as Community Projects including Fedora and Red Hat OpenShift AI.

Mitigation

To reduce the risk of exploitation, ensure that the ollama service processes GGUF metadata only from trusted and verified sources. Avoid loading or processing GGUF files from untrusted or unverified origins.

Common Vulnerability Scoring System (CVSS) Score Details

Info alert:Important note

CVSS scores for open source components depend on vendor-specific factors (e.g. version or build chain). Therefore, Red Hat's score and impact rating can be different from NVD and other vendors. Red Hat remains the authoritative CVE Naming Authority (CNA) source for its products and services (see Red Hat classifications).

The following CVSS metrics and score provided are preliminary and subject to review.

CVSS v3 Score Breakdown

Red HatNVDcve.org
Base Score7.5N/A7.5
Attack VectorNetworkN/ANetwork
Attack ComplexityLowN/ALow
Privileges RequiredNoneN/ANone
User InteractionNoneN/ANone
ScopeUnchangedN/AUnchanged
ConfidentialityNoneN/ANone
Integrity ImpactNoneN/ANone
Availability ImpactHighN/AHigh

Vector

Red Hat: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

cve.org: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H

Understanding the Weakness (CWE)

Confidentiality,Integrity

Technical Impact: Read Memory; Modify Memory; Varies by Context

Frequently Asked Questions

Want to get errata notifications? Sign up here.