Vulnerability · CVE-2026-7482
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader.
Published May 4, 2026 · corrected/updated Jun 17, 2026 · Ollama Ollama · evidence confidence very high
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).
Grounded briefings
Catalog interpretations for three audiences. Each brief cites ingested metadata and the original advisories below. They are not independent research and they do not invent exploit steps.
Executive
CVE-2026-7482 is a high public vulnerability record for Ollama Ollama. CISA lists it as known exploited. Published remediation guidance: Apply remediations or mitigations per vendor instructions or discontinue use of the product if remediation or mitigations are unavailable. This summary is a catalog interpretation of the ingested metadata and cites the original advisories below.
System administrator
Identify whether Ollama Ollama is in your estate, then compare installed versions with the affected ranges. Affected packages or ranges on record: ollama/ollama; Ollama Ollama. Published remediation guidance: Apply remediations or mitigations per vendor instructions or discontinue use of the product if remediation or mitigations are unavailable. Prefer the vendor or distribution advisory linked in Sources before changing production systems. This is a catalog interpretation, not a runbook.
Security analyst
Signals on file: CVSS 8.8, EPSS 0.7%. CISA lists it as known exploited. Weakness classes: CWE-125. Sources contributing to this record: cve_org, epss, nvd, vulncheck_kev. Public exploit references, when present, are outbound links only and are not proof of active exploitation. This is a catalog interpretation of stored metadata.
Exploitation and remediation
Exploitation evidence
Confirmed in CISA KEV since Jun 8, 2026. Listed in CISA KEV and VulnCheck KEV.
Patch and remediation
Apply remediations or mitigations per vendor instructions or discontinue use of the product if remediation or mitigations are unavailable.
Safe detection guidance
Compare installed versions with the affected ranges below and verify the advisory from the original publisher. This site stores metadata and outbound links only; it does not ship exploit code or proof-of-concept payloads.
Code
The project this record applies to. Exploit listings stay in References.
Timeline
Detection, updates, and resolution for this record.
May 4, 2026 · NIST NVD
Detected
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may inc
Jun 8, 2026 · CISA KEV
Known exploited
Apply remediations or mitigations per vendor instructions or discontinue use of the product if remediation or mitigations are unavailable.
Jun 17, 2026 · NIST NVD
Updated
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may inc
Affected
- cpe ollama/ollamaversion unspecified
- vendor Ollama Ollamaversion unspecified
Sources
- CVE.orgVulnerability recordCVE-2026-7482
Official CVE identifier
cve.org - FIRST EPSSExploitation probabilityCVE-2026-7482
30-day exploitation probability 0.7%
first.org - NIST NVDVulnerability recordCVE-2026-7482
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and
nvd.nist.gov - VulnCheck KEVConfirmed exploitationCVE-2026-7482
Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and
vulncheck.com