CVE-2024-12055
Memory Safety in Ollama ≤ 0.3.14
Raw vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:HCVSS and EPSS are reproduced from their sources (NVD, FIRST EPSS). Risk Priority is our own derived reading, not an NVD score.
Summary
CVE-2024-12055 is a high-severity Out-of-bounds Read (CWE-125) vulnerability in Ollama Ollama. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Data Obfuscation (T1001); ranked in the top 44% 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 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 SA-8 (Security and Privacy Engineering Principles) — 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-2024-12055 is a vulnerability in Ollama versions up to and including 0.3.14, stemming from an out-of-bounds read in the gguf.go file and classified under CWE-125. This flaw allows a malicious user to create a customized GGUF model file that can be uploaded to a public Ollama server. When the server processes the malicious model, it crashes, resulting in a Denial of Service (DoS) condition. The issue 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 availability impact.
Any unauthenticated attacker with network access can exploit this vulnerability due to its lack of prerequisite privileges or user interaction. By crafting and uploading the malicious GGUF model file to the public Ollama server, the attacker triggers the out-of-bounds read during model processing, causing the server to crash and disrupting service availability for all users.
For mitigation details, security practitioners should consult the advisory referenced at https://huntr.com/bounties/7b111d55-8215-4727-8807-c5ed4cf1bfbe, which documents the issue discovered through a bug bounty program. Upgrading to Ollama versions beyond 0.3.14 is implied as a resolution based on the affected version scope.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2025-7036
Vulnerability Data
A vulnerability in Ollama versions <=0.3.14 allows a malicious user to create a customized gguf model file that can be uploaded to the public Ollama server. When the server processes this malicious model, it crashes, leading to a Denial of…
more
Service (DoS) attack. The root cause of the issue is an out-of-bounds read in the gguf.go file.
- 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: ollama
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
Developer testing and evaluation directly finds out-of-bounds read flaws through static analysis, fuzzing, and dynamic bounds checks.
Secure engineering principles require bounds checking and memory-safe constructs that stop out-of-bounds reads from being introduced.
Process isolation confines the effects of an out-of-bounds read to the compromised process.
Input validation rejects malformed indices or lengths that would otherwise cause reads outside buffer bounds.
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.
Vulnerability scanning and recording can discover instances of out-of-bounds reads after code is deployed.
Routine patching replaces vulnerable code containing out-of-bounds read flaws.
Secure-development practices such as bounds checking and memory-safe languages directly prevent out-of-bounds reads.
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.