PT-2026-36799 · Ollama · Ollama

Published 2026-05-04 · Updated 2026-05-04 · CVE-2026-7482

NVD

CVSS v3.1

9.1

Critical

Base vector

AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

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).

Fix

Out of bounds Read

Weakness Enumeration

CWE-125

Related Identifiers

CVE-2026-7482

Affected Products

Ollama

References · 4

• https://github.com/ollama/ollama/commit/88d57d0483cca907e0b23a968c83627a20b21047 · Patch
• https://github.com/ollama/ollama/pull/14406 · Patch
• https://nvd.nist.gov/vuln/detail/CVE-2026-7482 · Security Note
• https://github.com/ollama/ollama/releases/tag/v0.17.1 · Note