Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · Ollama

CVE-2024-12055: Ollama Allows Out-of-Bounds Read

highCVSS 3.0 7.5GHSA-89qx-m49c-8crf

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 Service (DoS) attack. The root cause of the issue is an out-of-bounds read in the gguf.go file.

Published Mar 20, 2025 · Updated Mar 22, 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 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 Service (DoS) attack. The root cause of the issue is an out-of-bounds read in the gguf.go file.

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 entries