Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
Ollama (github.com/ollama/ollama) versions up to and including 0.3.3 contain a divide by zero flaw. An attacker who can supply a crafted GGUF model with a malicious block_count value in its Modelfile can crash the server during model processing, causing a denial of service. The source gives few details on who can supply such a model. No fix is listed, so the reader should avoid importing untrusted GGUF models.
Not analysed yet
We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.
Severity and exploitation
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 7.5 | High | 3.0 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | CNA (@huntr_ai) |
- CISA KEV Not listed.
- EPSS 0.0064, the 51st percentile, on 17 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:14 UTC First seen by agentprime
- 31 Oct 2026, 14:14 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-2xf2-gjm6-g2c6
- OSV: GHSA-2xf2-gjm6-g2c6
- nvd.nist.gov/vuln/detail/CVE-2024-8063
- github.com/ollama/ollama/issues/8020
- github.com/ollama/ollama
- github.com/pypa/advisory-database/tree/main/vulns/ollama/PYSEC-2025-144.yaml
- huntr.com/bounties/fd8e1ed6-21d2-4c9e-8395-2098f11b7db9