SEPTEMBER 5, 2026
Live Feed
Back to database
Case File

CVE-2026-65315

HIGH · CVSS 7.5 EPSS 0.57% Public Exploit

Source: NVD + CISA KEV + EPSS · Published 2026-07-21 · Last synced 2026-08-20

CyberRota Analysis

AI-Generated

Ollama's GGUF metadata parser is vulnerable to an uncontrolled memory allocation issue, allowing remote attackers to crash the server by uploading specially crafted GGUF files with manipulated length and count fields. This can lead to unrecoverable out-of-memory errors or panics, resulting in a complete server crash. Organizations using Ollama should prioritize patching this vulnerability to prevent potential service disruptions and ensure system stability.

Public Exploit Signal

A public exploit, PoC, GitHub repository or Metasploit reference was detected for this CVE.

Note: these links are listed for security research and verification purposes only.

CVE
CVE-2026-65315
Severity
HIGH
CVSS
7.5
EPSS
0.57%

Original NVD Description

Ollama (HEAD f0078ae) contains an uncontrolled memory allocation vulnerability in the GGUF metadata parser that allows remote attackers to crash the server by supplying a crafted GGUF file with attacker-controlled length and count fields in string lengths, tensor dimension counts, and metadata array counts that are used as allocation sizes without validation against remaining file size. Attackers can upload a sub-1KB crafted GGUF file via the blob upload and model create or pull API endpoints to trigger unrecoverable Go runtime out-of-memory fatal errors or makeslice panics that bypass recovery middleware and crash the entire server process.