Black Friday60% off BLACKFRIDAY2026
PlatformPlansPartners
Resources
ToolsBlogDocs
Sign Up →
critical·Misconfiguration·Updated Nov 12, 2026

CVE-2026-7482 Scanner

CVE-2026-7482 Scanner - Information Disclosure vulnerability in Ollama

Est. Time~10 seconds
Scan TypeGroup Scan
Targetsurl
CostFree
3
Times Used
continuous scan runs
4.2k
Continuously Checked
assets under CS
0
Vulnerabilities Found
confirmed findings
References
8.8
CVSScritical
Exploitable remotely over the internet · no authentication required.
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).

Attack Vector
Network
Privileges Req.
None
User Interaction
None
Affected
ollamaby ollama
AFFECTED< 0.17.1→SAFE ✓≥ 0.17.1
Updated Nov 12, 2026View on NVD →
Detail

Ollama is a widely-used software solution often employed for data processing and machine learning tasks. It is designed to provide users with efficient tools and interfaces for managing and deploying AI models. Utilized by developers and data scientists, Ollama aims to streamline operations by offering integration capabilities with various data sources. Its functionalities are essential in industries that require sophisticated data analysis, such as finance, healthcare, and technology. The product's expansive feature set accommodates diverse use cases, making it a valuable tool in the tech community. With frequent updates and improvements, Ollama remains a key player in AI model management and deployment.

The vulnerability identified in Ollama is an Information Disclosure issue in versions below 0.17.1. This flaw is due to a heap out-of-bounds read caused by improper validation of tensor offset and size. Attackers leveraging this vulnerability can access sensitive memory data, leading to exposure of confidential information. The issue is particularly concerning because it requires no authentication to exploit. This vulnerability can potentially lead to significant data breaches if left unaddressed. Proper measures and updates are necessary to mitigate the risk associated with this flaw.

The technical details of this vulnerability include improper checks on tensor offsets and sizes within the GGUF model loader. The affected endpoints, /api/create and /api/push, are vulnerable to this flaw, enabling remote attackers to read beyond the intended memory bounds. This improper handling allows for the extraction of sensitive information like environment variables and API keys. Due to the ease of exploitation, attackers can initiate the exploit without needing authenticated access. The vulnerability's presence in critical endpoints underscores the need for stringent validation processes in software development. Addressing the issue involves updating the software to a secure version.

Exploitation of this vulnerability can result in severe consequences, including data breaches and loss of confidential user information. Malicious actors could obtain environment details, API keys, and personal user data. Such breaches may lead to unauthorized access to systems, financial loss, and reputational damage. The information obtained can be used to conduct further attacks, compromising additional systems. Organizations utilizing vulnerable versions of the software risk exposing sensitive business data to external threats. Consequently, addressing this vulnerability promptly is crucial to safeguard against its potential impacts.

REFERENCES

Solution Advice
  • Update Ollama to version 0.17.1 or later.
  • Regularly review and patch software to mitigate vulnerabilities promptly.
  • Implement robust validation checks in software deployment processes.
  • Conduct regular security audits to identify and rectify potential flaws.
  • Enhance logging and alert mechanisms to detect exploitation attempts early.

Get AI-powered remediation steps tailored to your asset.

Try AI Solutions →

Check your infrastructure.
Right now.

12,000+ scanners. Free to start. No credit card required.