PatchSiren

PatchSiren cyber security CVE debrief

CVE-2026-65315 Ollama CVE debrief

CVE-2026-65315 is a high-severity vulnerability in the Ollama project's GGUF metadata parser. The vulnerability allows remote attackers to crash the server by supplying a crafted GGUF file with attacker-controlled length and count fields. This vulnerability is triggered through the blob upload and model create or pull API endpoints. Successful exploitation requires the attacker to upload a sub-1KB crafted GGUF file, which can lead to unrecoverable Go runtime out-of-memory fatal errors or makeslice panics, bypassing recovery middleware and crashing the entire server process. Organizations should prioritize patching this vulnerability to prevent potential denial-of-service attacks.

Vendor
Ollama
Product
Unknown
CVSS
HIGH 8.7
CISA KEV
Not listed in stored evidence
Original CVE published
2026-07-21
Original CVE updated
2026-07-22
Advisory published
2026-07-21
Advisory updated
2026-07-22

Who should care

Organizations using Ollama, especially those exposed to untrusted input, should prioritize patching this vulnerability to prevent potential denial-of-service attacks. This includes operators of Ollama deployments, security teams responsible for vulnerability management, and platform administrators who may be impacted by the vulnerability. Additionally, defenders should verify the authenticity of GGUF files and monitor for suspicious activity on the blob upload and model create or pull API endpoints.

Technical summary

The vulnerability is caused by an uncontrolled memory allocation in the GGUF metadata parser. When a crafted GGUF file with attacker-controlled length and count fields is supplied, it can lead to unrecoverable Go runtime out-of-memory fatal errors or makeslice panics, crashing the entire server process. The vulnerability is triggered via the blob upload and model create or pull API endpoints. The GGUF file can be uploaded by an attacker, who can then cause a denial-of-service condition. The vulnerability has not been extensively analyzed yet, but preliminary evidence suggests that it could be exploited through specially crafted GGUF files.

Defensive priority

High

Recommended defensive actions

  • Apply the vendor patch as soon as available
  • Restrict access to the blob upload and model create or pull API endpoints
  • Monitor for suspicious activity on these endpoints
  • Implement additional logging and monitoring to detect potential attacks
  • Review compensating controls for exposed systems while remediation is scheduled and verified
  • Check relevant monitoring, detection, and logs for exposed assets that need extra review
  • Track exceptions, retest remediated assets, and close the item only after evidence is documented

Evidence notes

The CVE record was published on 2026-07-21T22:19:10.050Z and last modified on 2026-07-22T20:40:02.810Z. The NVD entry is currently Awaiting Analysis. References include the Ollama GitHub repository, an issue report, and a Vulncheck advisory. The vulnerability has not been extensively analyzed yet, but preliminary evidence suggests that it could be exploited through specially crafted GGUF files. Defenders should verify the authenticity of GGUF files and monitor for suspicious activity. Evidence is limited, and further analysis is required to fully understand the vulnerability and its potential impact.

Sources and references

Verified primary and authoritative sources

  • CVE-2026-65315 CVE Program record

    Publisher, destination, and source semantics verified

    URL: https://www.cve.org/CVERecord?id=CVE-2026-65315

    CVE Program - Official CVE Program record with source-provided CVE metadata.

  • CVE-2026-65315 NVD vulnerability detail

    Publisher, destination, and source semantics verified

    URL: https://nvd.nist.gov/vuln/detail/CVE-2026-65315

    NIST National Vulnerability Database - Official NIST NVD detail page and source-specific vulnerability assessment.

Supplemental references

Methodology and review provenance

AI-assisted synthesis based on stored public vulnerability evidence. System validation, approval state, and publication status do not by themselves establish human review of this revision. PatchSiren helps prioritize defensive review and does not prove exposure or remediation on any system.