8.7
High
CVE-2026-65315 Ollama (HEAD f0078ae) contains an uncontrolled memory allocation vulnerability in the GGUF metadata parser that allows…
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.
Affected products and versions
| Product | Affected versions | Fixed in |
|---|---|---|
| Ollama | Versions not published |
Other CVEs of Ollama
The 14 CVEs of Ollama →
CVE-2026-103663
Ollama is vulnerable to path traversal in the `/api/pull` endpoint due to insufficient validation of layer digests by…
6.9
Medium
CVE-2026-102697
Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode…
8.5
High
CVE-2026-85180
Ollama fails to validate redirect destinations when pulling tensor-layer models, allowing unauthenticated attackers to…
8.7
High
CVE-2026-15685
Ollama downloadBlob Improper Validation of Array Index Denial-of-Service Vulnerability
7.5
High