CVE-2025-0315: Ollama Allocation of Resources Without Limits or Throttling vulnerability
A vulnerability in ollama/ollama <=0.3.14 allows a malicious user to create a customized GGUF model file, upload it to the Ollama server, and create it. This can cause the server to allocate unlimited memory, leading to a Denial of Service (DoS) attack.
Published Mar 20, 2025 · Updated Mar 21, 2025
Affected packages
github.com/ollama/ollama
- Ecosystem
- Go
- Affected
- <= 0.3.14
- Fixed in
- No patched version yet
- Check
go list -m github.com/ollama/ollama
Advisory details
From the GitHub Advisory Database (CC BY 4.0).
A vulnerability in ollama/ollama <=0.3.14 allows a malicious user to create a customized GGUF model file, upload it to the Ollama server, and create it. This can cause the server to allocate unlimited memory, leading to a Denial of Service (DoS) attack.
References
How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology
More Ollama vulnerabilities
All Ollama entriesCVE-2026-7482
Ollama contains a heap out-of-bounds read vulnerability in the GGUF model loader
high9.1May 4, 2026CVE-2026-7020
Ollama is Vulnerable to Path Traversal
low5.6No fixApr 26, 2026CVE-2025-63389
Ollama Platform has missing authentication enabling attackers to perform model management operations
critical9.3No fixDec 18, 2025CVE-2025-44779
Ollama allows deletion of arbitrary files
medium6.6Aug 7, 2025CVE-2025-51471
Ollama vulnerable to Cross-Domain Token Exposure
medium6.9No fixJul 22, 2025CVE-2025-1975
Ollama Server Vulnerable to Denial of Service (DoS) Attack
high7.5No fixMay 16, 2025