Cyber Resilience

CVE-2025-66960

DoS in Ollama 0.12.10

Public PoCDoS
Published
21 January 2026
Modified
02 February 2026
Patch / advisory
CVSS Score v3.1 7.5
Click a component to see what it means
Raw vectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H
EPSS Score 0.0036 29th percentile
Risk Priority 58 floored blend · peak EPSS

Summary

CVE-2025-66960 is a high-severity Improper Input Validation (CWE-20) vulnerability in Ollama Ollama. Its CVSS base score is 7.5 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique OS Exhaustion Flood (T1499.001); ranked at the 29th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as NLP and Transformers; in the Data-Related Vulnerabilities risk domain.

The strongest mitigations our analysis identified map to SA-11 (Developer Testing and Evaluation) and SC-5 (Denial-of-service Protection) — see the control section below for these in your framework.

Deeper analysis AI-assisted summary

Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.

CVE-2025-66960 is a denial-of-service vulnerability affecting Ollama version 0.12.10. The issue resides in the fs/ggml/gguf.go file, specifically the readGGUFV1String function, which reads a string length directly from untrusted GGUF metadata without proper validation. This flaw, associated with CWE-20 (Improper Input Validation) and CWE-400 (Uncontrolled Resource Consumption), carries a CVSS v3.1 base score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H) and was published on 2026-01-21T18:16:23.950.

A remote attacker can exploit this vulnerability without authentication privileges or user interaction by supplying malicious GGUF metadata to an Ollama instance listening over the network. Successful exploitation triggers a panic or resource exhaustion in the readGGUFV1String function, resulting in high-impact denial of service that crashes the service or renders it unavailable.

Mitigation details are available in the referenced advisories, including the Ollama GitHub issue at https://github.com/ollama/ollama/issues/9820 and the technical analysis at https://zero.shotlearni.ng/blog/cve-2025-66960guf-v1-string-length-cause-panic-in-readggufv1string/.

OWASP Top 10 for Web (2025)

EU & UK References

Vulnerability Data

An issue in ollama v.0.12.10 allows a remote attacker to cause a denial of service via the fs/ggml/gguf.go, function readGGUFV1String reads a string length from untrusted GGUF metadata

CWE(s)

AI Security AnalysisAI

AI Category
NLP and Transformers
Risk Domain
Data-Related Vulnerabilities
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Matched keywords: ggml, ollama

Related Threats

MITRE ATT&CK Enterprise Techniques

T1499.001 OS Exhaustion Flood Impact
Adversaries may launch a denial of service (DoS) attack targeting an endpoint's operating system (OS).
T1190 Exploit Public-Facing Application Initial Access
Adversaries may attempt to exploit a weakness in an Internet-facing host or system to initially access a network.
T1498 Network Denial of Service Impact
Adversaries may perform Network Denial of Service (DoS) attacks to degrade or block the availability of targeted resources to users.
T1499 Endpoint Denial of Service Impact
Adversaries may perform Endpoint Denial of Service (DoS) attacks to degrade or block the availability of services to users.
T1499.002 Service Exhaustion Flood Impact
Adversaries may target the different network services provided by systems to conduct a denial of service (DoS).
T1499.003 Application Exhaustion Flood Impact
Adversaries may target resource intensive features of applications to cause a denial of service (DoS), denying availability to those applications.
Derived from this CVE’s CWE(s) via the direct CWE→ATT&CK cross-walk.

CVEs Like This One

CVE-2025-66959Same product: Ollama Ollama
CVE-2025-44779Same product: Ollama Ollama
CVE-2026-50196Shared CWE-20, CWE-400
CVE-2023-22470Shared CWE-20, CWE-400
CVE-2025-21230Shared CWE-20, CWE-400
CVE-2023-45167Shared CWE-20, CWE-400
CVE-2023-42503Shared CWE-20, CWE-400
CVE-2026-33287Shared CWE-20, CWE-400
CVE-2026-33285Shared CWE-20, CWE-400
CVE-2023-27483Shared CWE-20, CWE-400

Affected Assets

ollama
ollama
0.12.10

Mitigating Controls

Control response

Prevent
Stop it (NIST 800-53)

Detect
Catch it (NIST detect / respond)

Harden
Shrink the surface (DISA STIG)
  • 6 hardening rules · 3 OS baselines
Validate
Prove the fix (OWASP ASVS)

Mitigating Controls (NIST 800-53 r5) AI

Developer testing and evaluation can discover missing input validation through analysis or test cases.

SC-5 directly limits the effects of resource-exhaustion events that constitute uncontrolled consumption.

SC-6 enforces explicit allocation limits on resources, structurally preventing the weakness from occurring.

SI-10 directly requires validity checks on information inputs, structurally preventing improper or missing validation.

Requiring documented development standards and tools can embed input-validation practices into the engineering process.

Process isolation confines resource consumption to separate domains, reducing blast radius without stopping the root flaw.

Mitigating Controls (NIST CSF 2.0) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.

PR.IR-04 mostly match
prevents

Explicitly requires monitoring and maintaining resource capacity, directly addressing uncontrolled consumption to preserve availability.

PR.PS-06 mostly match
prevents

Secure SDLC practices directly require and enforce input validation during development.

DE.CM-09 partial match
prevents

Continuous monitoring of computing resources can detect resource exhaustion but does not itself enforce allocation limits.

PR.IR-03 partial match
prevents

Resilience mechanisms such as avoiding single points of failure indirectly reduce impact of resource exhaustion.

PR.PS-01 partial match
prevents

Hardened configuration baselines can include resource quotas and limits that constrain consumption.

Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI

Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.

finds

Resource-utilization monitoring and alerting on bottlenecks or overloads limits the impact of denial-of-service or resource-exhaustion attacks.

finds

Testing against a defined set of requirements and using code review plus vulnerability scanning forces validation of inputs and handling of unanticipated conditions, reducing the chance that malformed data will be accepted.

prevents

By continuously monitoring utilization, stress-testing peak loads, and maintaining documented plans to scale or throttle resources, the control directly limits an attacker’s ability to drive a system into uncontrolled resource exhaustion.

finds

Pre-agreed severity-based prioritization and resource allocation during incident triage reduce the likelihood that an attacker-induced resource exhaustion will overwhelm the organization before corrective action is taken.

mitigates

Business-continuity plans that include resource-management controls reduce the likelihood that an attacker can trigger uncontrolled resource consumption by forcing the system into a degraded or fallback state.

mitigates

Defining RTOs and capacity requirements for ICT services during business-impact analysis forces organizations to provision sufficient resources and throttling mechanisms, reducing the likelihood that an attacker can induce denial-of-service through uncontrolled resource consumption.

Hardening callouts derived

Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (authoritative rows only; rows rated `none` are excluded).

RHEL 8 (1 rule)
  • V-230265 RHEL 8 must prevent the installation of software, patches, service packs, device drivers, or operating system components of local packages without verification they have been digitally signed using a certificate that is issued by a Certificate Authority (CA) that is recognized and approved by the organization. prevents CWE-20

References