# Ollama Divide by Zero Vulnerability

Advisory record · `GHSA-2xf2-gjm6-g2c6`

- **Identifiers:** `GHSA-2xf2-gjm6-g2c6` · `CVE-2024-8063` · `GO-2025-3689` · `PYSEC-2025-144`
- **State:** Confirmed
- **Severity:** CVSS 7.5 High
- **Critical:** No
- **Weakness (CWE):** [CWE-369](https://cwe.mitre.org/data/definitions/369.html)
- **Tags:** [Denial of service](https://agentprime.io/advisories/tag/dos.md)
- **Published:** 20 Mar 2025
- **Updated:** 10 Sept 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 20 Mar 2025, 12:32 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `github.com/ollama/ollama` (Go): affected `<=0.3.3`; no fixed version yet

## 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.

Written 1 Nov 2026.

## 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

- 7.5 High, CVSS 3.0: `CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H`, from 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](https://osv.dev/vulnerability/GHSA-2xf2-gjm6-g2c6)

## Sources

- [GitHub Advisory Database: GHSA-2xf2-gjm6-g2c6](https://github.com/advisories/GHSA-2xf2-gjm6-g2c6)
- [OSV: GHSA-2xf2-gjm6-g2c6](https://osv.dev/vulnerability/GHSA-2xf2-gjm6-g2c6)
- <https://nvd.nist.gov/vuln/detail/CVE-2024-8063>
- <https://github.com/ollama/ollama/issues/8020>
- <https://github.com/ollama/ollama>
- <https://github.com/pypa/advisory-database/tree/main/vulns/ollama/PYSEC-2025-144.yaml>
- <https://huntr.com/bounties/fd8e1ed6-21d2-4c9e-8395-2098f11b7db9>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-2xf2-gjm6-g2c6>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-2xf2-gjm6-g2c6/>. Everything for agents: <https://agentprime.io/llms.txt>.
