All vulnerabilities

Servers and applications

CVE-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 server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may…

Severity
High 8.8
Published
4 May 2026
Last changed
11 Nov 2026
Added to UpHeron
1 Nov 2026
Fixed in
0.17.1
Exploit chance
7.1% in the next 30 daysHigher than 94% of CVEs. EPSS by FIRST, 19 Nov 2026
Weakness
Out-of-bounds read (CWE-125)
Attack
Over the network · No login needed · No user action needed
Attacker can
Read data · Take it down
CVSS vector
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:Y/R:A/V:D/RE:L/U:Red
Sources
NVD

Description

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).

From NVD.

Affected software

SoftwareAffected versions
OllamaServers and applications · cpe:a:ollama:ollama
  • Every version before 0.17.1

About Ollama

software for running large language models (LLMs) on a local computer or in the cloud

From Wikidata, CC0 1.0.
Docker Hub pulls
200,724,007Docker Hub, 15 Nov 2026
GitHub stars
187,005GitHub, 15 Nov 2026
Forks
19,091GitHub, 15 Nov 2026
Latest release
v0.40.16GitHub, 15 Nov 2026
Released
9 Nov 2026GitHub
License
MIT LicenseWikidata
Written in
GoWikidata
First released
8 Jul 2023Wikidata
First published on GitHub
26 Jun 2023GitHub

Vulnerabilities in Ollama

In our list
28
Published in the last 12 months
13
Critical, last 12 months
1
High, last 12 months
9
Known exploited
0
Search the list for Ollama

References

  • NVD https://nvd.nist.gov/vuln/detail/CVE-2026-7482
  • CVE.org https://www.cve.org/CVERecord?id=CVE-2026-7482