CVE-2026-7482
🗓️ 04 May 2026 12:38:28Reported by EchoType 
cve🔗 web.nvd.nist.gov📰️ 12 Media mentions👁 228 Views🌐 WEB
| Reporter | Title | Published | Views | Family All 47 |
|---|---|---|---|---|
 | Exploit for CVE-2026-7482 | 5 May 202619:55 | – | githubexploit |
| Exploit for CVE-2026-7482 | 7 May 202616:35 | – | githubexploit |
| ollama-silent-patches | 9 Jun 202622:07 | – | githubexploit |
 | CVE-2026-7482 | 4 May 202612:38 | – | attackerkb |
 | CVE-2026-7482 | 4 May 202612:38 | – | alpinelinux |
 | Ollama Loader Unauthenticated Access | 10 Jun 202600:00 | – | bdu_fstec |
 | CVE-2026-7482 vulnerabilities | 9 May 202613:17 | – | cgr |
 | CVE-2026-7482 | 4 May 202614:15 | – | circl |
 | Ollama buffer error vulnerability | 4 May 202600:00 | – | cnnvd |
 | Ollama GGUF Model Loader Heap Out-of-Bounds Read Vulnerability | 6 May 202600:00 | – | cnvd |
10
[
{
"vendor": "ollama",
"product": "ollama",
"packageName": "ollama/ollama",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "0.17.1",
"versionType": "semver"
}
],
"defaultStatus": "unaffected",
"collectionURL": "https://github.com",
"repo": "https://github.com/ollama/ollama",
"programFiles": [
"fs/ggml/gguf.go",
"server/quantization.go"
]
}
]| Parameter | Position | Path | Description | CWE |
|---|---|---|---|---|
| name | request body | /api/create | Heap out-of-bounds read in the GGUF model loader. By providing a maliciously crafted GGUF file (via /api/blobs/) that declares a tensor size exceeding the actual file length, an attacker can trigger a heap OOB read during the quantization process (e.g., when using quantize=Q8_0). | CWE-125 |
| files | request body | /api/create | Heap out-of-bounds read in the GGUF model loader. By providing a maliciously crafted GGUF file (via /api/blobs/) that declares a tensor size exceeding the actual file length, an attacker can trigger a heap OOB read during the quantization process (e.g., when using quantize=Q8_0). | CWE-125 |
| quantize | request body | /api/create | Heap out-of-bounds read in the GGUF model loader. By providing a maliciously crafted GGUF file (via /api/blobs/) that declares a tensor size exceeding the actual file length, an attacker can trigger a heap OOB read during the quantization process (e.g., when using quantize=Q8_0). | CWE-125 |
| sha256:<hash> | upload data | /api/blobs/sha256:<hash> | Endpoint used to upload the malicious GGUF file. The file contains a declared tensor offset and size that exceed the file's actual length, which is then processed by the /api/create endpoint. | CWE-125 |
10
Data
Build on a solid foundation with Vulners data
We provide the essential building blocks for cybersecurity solutions with comprehensive, structured, and constantly updated vulnerability and exploits data
Api
Power your application with Vulners API
The Vulners REST API offers reliable, high-performance access to vulnerability intelligence, with 99.9% SLA uptime and CDN-backed data delivery for seamless global access
App
Assess and manage vulnerabilities with Vulners tools
Built on top of Vulners' database and SDK, end-user solutions give security professionals and developers lightweight and powerful tools for vulnerability remediation
17 Jun 2026 11:02Current
6.8Medium risk
Vulners AI Score6.8
CVSS 48.8
CVSS 3.19.1
EPSS0.02241
SSVC