Unauthenticated heap disclosure via unchecked tensor metadata
Published Jun 26, 2026 · Updated Jun 26, 2026
Out-of-bounds read in Ollama 0.13.5 allows remote attackers to exfiltrate server heap memory through a crafted GGUF model. The quantizer trusts attacker-controlled tensor element counts, passes them to Go's unsafe.Slice without checking the backing data size, and writes exposed heap contents into a new model layer. Access to the model upload and quantization interfaces is required; the resulting layer can be pushed through Ollama's registry API to an attacker-controlled server.
Summary
What happened
Out-of-bounds read in Ollama 0.13.5 allows remote attackers to exfiltrate server heap memory through a crafted GGUF model. The quantizer trusts attacker-controlled tensor element counts, passes them to Go's unsafe.Slice without checking the backing data size, and writes exposed heap contents into a new model layer. Access to the model upload and quantization interfaces is required; the resulting layer can be pushed through Ollama's registry API to an attacker-controlled server.
The record
- CVE
- CVE-2026-5757
- Published
- Jun 26, 2026
- Updated
- Jun 26, 2026
- Vendor
- Ollama
- Product
- Ollama
- Classifications
- CWE-125, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jun 26, 2026CVE publishedPublication date reported by the CVE source.
- Jun 26, 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=v0.13.5
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.
Public exploit references
No public exploit references are available in this record.
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