What is CVE-2024-39720?
An issue was discovered in Ollama before 0.1.46. An attacker can use two HTTP requests to upload a malformed GGUF file containing just 4 bytes starting with the GGUF custom magic header. By leveraging a custom Modelfile that includes a FROM statement pointing to the attacker-controlled blob file, the attacker can crash the application through the CreateModel route, leading to a segmentation fault (signal SIGSEGV: segmentation violation).
The record classifies CVE-2024-39720 under weakness class CWE-125. Its CVSS v3 base vector states that the flaw is reachable remotely over the network, needs no prior authentication, needs no user interaction, and has high impact on availability. 1 affected-product entry is recorded, across 1 vendor, listed below. The identifier was first published 749 days ago.
Severity and exploitation probability
- CVSS v3.1 base score
- 8.2 — HIGH
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:H - EPSS (FIRST)
- 2.4% probability of exploitation in the next 30 days, higher than 83.8% of all scored CVEs
- CISA KEV
- Not listed in the CISA Known Exploited Vulnerabilities catalog
- Threadlinqs priority
- 9.5/10 — a Threadlinqs composite of the CVSS base score, the EPSS percentile and public exploit availability
- Published
- 2024-10-31
Is CVE-2024-39720 being exploited?
Weaponised exploit code for CVE-2024-39720 is publicly available. 1 public proof-of-concept repository is tracked for this identifier. It currently carries a trending score of 34 in the Threadlinqs vulnerability feed.
- trickest/cve (trickest)
Affected products and versions
- Ollama: Ollama
How to fix CVE-2024-39720
The record marks a vendor fix as available for CVE-2024-39720. Patch reference: https://github.com/ollama/ollama/releases. Apply the vendor fix referenced above to every affected product listed in this record, then confirm the running version against the vendor advisory.
Threat activity tracking CVE-2024-39720
2 tracked threats in the Threadlinqs corpus reference CVE-2024-39720, either in the campaign’s CVE list or as an indicator on the campaign record.
- LLMJacking: 175,000 Exposed Ollama AI Servers Targeted for Abuse — HIGH · 2026-02-02
Sources
Enriched from CVE.org, FIRST EPSS, public proof-of-concept repositories.