CVE-2025-0312
Published: 20 March 2025
Summary
CVE-2025-0312 is a high-severity NULL Pointer Dereference (CWE-476) vulnerability in Ollama Ollama. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Application or System Exploitation (T1499.004); ranked at the 43.0th 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 APIs and Models; in the Supply Chain and Deployment risk domain.
The strongest mitigations our analysis identified are NIST 800-53 SC-5 (Denial-of-service Protection) and SI-10 (Information Input Validation).
Threat & Defense at a Glance
Threat & Defense Details
Mitigating Controls (NIST 800-53 r5)AI
Flaw remediation requires applying patches to Ollama versions >0.3.14 to directly fix the unchecked null pointer dereference vulnerability.
Information input validation checks uploaded GGUF model files for malformed structures that could trigger the null pointer dereference crash.
Denial-of-service protection implements rate limiting and resource controls on model uploads to mitigate repeated crash attempts.
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
The vulnerability enables remote denial of service by crashing the Ollama server application through exploitation of an unchecked null pointer dereference when processing a malicious GGUF model file.
NVD Description
A vulnerability in ollama/ollama versions <=0.3.14 allows a malicious user to create a customized GGUF model file that, when uploaded and created on the Ollama server, can cause a crash due to an unchecked null pointer dereference. This can lead…
more
to a Denial of Service (DoS) attack via remote network.
Deeper analysisAI
CVE-2025-0312 is a vulnerability in ollama/ollama versions up to and including 0.3.14 that results from an unchecked null pointer dereference (CWE-476). A malicious user can create a customized GGUF model file, which, when uploaded and processed on the Ollama server, triggers the dereference and causes a crash.
The vulnerability 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), meaning it can be exploited remotely over the network with low attack complexity and no privileges or user interaction required. An unauthenticated attacker can upload the malicious GGUF model file to the server, achieving a Denial of Service (DoS) by crashing the service and disrupting availability.
Mitigation details are available in the referenced advisory at https://huntr.com/bounties/522c87b6-a7ac-41b2-84f3-62fd58921f21.
Details
- CWE(s)
Affected Products
AI Security AnalysisAI
- AI Category
- APIs and Models
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Ollama is an open-source platform for local deployment, management, and serving of LLMs using GGUF model files, fitting the 'Other Platforms' category as it provides runtime and API services for AI models.