Process-memory disclosure via malformed GGUF tensor offsets
Published May 4, 2026 · Updated May 4, 2026
Heap out-of-bounds read in Ollama before 0.17.1 allows remote attackers to disclose server process memory via a crafted GGUF file. The GGUF loader trusts declared tensor offsets and sizes, so WriteTo quantization reads beyond the uploaded file's allocated heap buffer. An unauthenticated network path exists only when the normally loopback-bound API is exposed; generated model artifacts can carry process-memory data to an attacker-controlled registry.
Summary
What happened
Heap out-of-bounds read in Ollama before 0.17.1 allows remote attackers to disclose server process memory via a crafted GGUF file. The GGUF loader trusts declared tensor offsets and sizes, so WriteTo quantization reads beyond the uploaded file's allocated heap buffer. An unauthenticated network path exists only when the normally loopback-bound API is exposed; generated model artifacts can carry process-memory data to an attacker-controlled registry.
The record
- CVE
- CVE-2026-7482
- Published
- May 4, 2026
- Updated
- May 4, 2026
- Vendor
- Ollama
- Product
- Ollama
- Classifications
- CWE-125, CAPEC-540, T1190, T1212
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 4, 2026CVE publishedPublication date reported by the CVE source.
- May 4, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <0.17.1
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Ollama GGUF Heap OOB Read Reproductionproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo