CVE-2025-0315
Published: 20 March 2025
Description
Adversaries may exploit software vulnerabilities that can cause an application or system to crash and deny availability to users.
Security Summary
CVE-2025-0315 is a vulnerability in ollama/ollama versions up to and including 0.3.14. It enables a malicious user to craft a customized GGUF model file, upload it to the Ollama server, and create it, triggering unlimited memory allocation on the server. This results in a Denial of Service (DoS) condition due to memory exhaustion. The issue is tracked under CWE-770 and 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), highlighting its high-impact availability disruption.
An unauthenticated attacker can exploit this vulnerability remotely over the network with low attack complexity and without requiring user interaction. By uploading and creating the malicious GGUF model file via the Ollama server, the attacker causes excessive memory consumption, crashing the server and denying service to other users or applications relying on it.
Further details on the vulnerability, including potential mitigations, are available in the Huntr bounty advisory at https://huntr.com/bounties/da414d29-b55a-496f-b135-17e0fcec67bc. The vulnerability was published on 2025-03-20.
Details
- CWE(s)
Affected Products
AI Security Analysis
- AI Category
- APIs and Models
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- MITRE ATLAS Techniques
- None mapped
- Classification Reason
- Ollama is an AI platform providing APIs for managing and running LLMs locally, with the vulnerability occurring during model file (GGUF) upload and creation on the server.
MITRE ATT&CK Enterprise Techniques
Why these techniques?
The vulnerability enables denial of service by allowing upload of a malicious GGUF model file that triggers unlimited memory allocation in the Ollama server application, facilitating endpoint DoS via application exploitation.