FlawAtlas
Search the atlas
CVE-2026-7482 High

Ollama contains a heap out-of-bounds read vulnerability in the GGUF model loader in github.com/ollama/ollama

Ollama is vulnerable to a heap out-of-bounds read in its GGUF model loader. A specially crafted GGUF file can cause the loader to read beyond the allocated heap buffer, potentially leading to a denial of service (crash).

Exploit probability 1.9%
Published July 27, 2026
Required by Not available
Last source change July 27, 2026

02 / AFFECTED SOFTWARE

Affected packages

Unknown Unknown

422 explicit affected versions

Go github.com/ollama/ollama
Go github.com/ollama/ollama

03 / CONNECTIONS

Connected vulnerabilities

04 / EVIDENCE

Source records

Open Source Vulnerabilities GHSA-x8qc-fggm-mpqg

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).

View original source
Open Source Vulnerabilities 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 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).

View original source
Open Source Vulnerabilities GO-2026-5748

Ollama is vulnerable to a heap out-of-bounds read in its GGUF model loader. A specially crafted GGUF file can cause the loader to read beyond the allocated heap buffer, potentially leading to a denial of service (crash).

View original source

05 / REFERENCES

Further evidence