Cyber Resilience

CVE-2024-39720

HighPublic PoC

Published: 31 October 2024

Published
31 October 2024
Modified
13 May 2025
KEV Added
—
Patch
—
CVSS Score v3.1 8.2 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H
EPSS Score 0.0029 52.4th percentile
Risk Priority 17 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2024-39720 is a high-severity Out-of-bounds Read (CWE-125) vulnerability in Ollama Ollama. Its CVSS base score is 8.2 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique File and Directory Discovery (T1083); ranked in the top 47.6% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as Other Platforms; in the LLM/Generative AI Risks risk domain; MITRE ATLAS techniques in scope: External Harms (AML.T0048).

EU & UK References

Vulnerability details

An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a…

more

FROM statement pointing to the attacker-controlled blob file, the attacker can crash the application through the CreateModel route, leading to a segmentation fault (signal SIGSEGV: segmentation violation).

CWE(s)
CWE-125

AI Security AnalysisAI

AI Category
Other Platforms
Risk Domain
LLM/Generative AI Risks
OWASP Top 10 for LLMs 2025
None mapped
Classification Reason
Ollama is an open-source platform/framework for running large language models (LLMs) locally, supporting inference on CPUs/GPUs, with APIs for model management (pull/push/create). The vulnerability involves malformed GGUF model files (LLM format) causing DoS during model creation/loading.

Related Threats

MITRE ATT&CK Enterprise TechniquesAI

T1083 File and Directory Discovery Discovery
Adversaries may enumerate files and directories or may search in specific locations of a host or network share for certain information within a file system.
attack.mitre.org →
T1499.004 Application or System Exploitation Impact
Adversaries may exploit software vulnerabilities that can cause an application or system to crash and deny availability to users.
attack.mitre.org →
T1105 Ingress Tool Transfer Command And Control
Adversaries may transfer tools or other files from an external system into a compromised environment.
attack.mitre.org →
T1567 Exfiltration Over Web Service Exfiltration
Adversaries may use an existing, legitimate external Web service to exfiltrate data rather than their primary command and control channel.
attack.mitre.org →
Why these techniques?

CVE-2024-39720 and CVE-2024-39721 enable DoS via application exploitation (crashes, out-of-bounds, loops); CVE-2024-39719/39722 enable file/directory discovery via disclosures/path traversal; shadow vulns allow unverified model pull (ingress tool transfer) and unauthorized model push (exfiltration over web service).

MITRE ATLAS TechniquesAI

MITRE ATLAS techniques

AML.T0048: External Harms

Affected Assets

ollama
ollama
≤ 0.1.46

Mitigating Controls

No mitigating controls mapped yet. The per-CVE control annotator has not reached this CVE.

References