CVE-2026-7482
CriticalSummary
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 where the declared tensor offset and size exceed the file's actual length, leading to reading memory past the allocated buffer.
Risk Assessment
This vulnerability may lead to the exposure of sensitive data such as environment variables, API keys, and user conversation data. Additionally, the lack of authentication in the /api/create and /api/push endpoints increases the risk of data exfiltration by an attacker.
Recommendation
It is recommended to update Ollama to version 0.17.1 or later and implement proper authentication mechanisms for the API endpoints. Consider restricting server access to trusted IP addresses only.
Original NVD description (English source)
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).