Ollama heap out-of-bounds read in GGUF tensor parsing leaks server process memory to unauthenticated remote attackers

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).

Scores

EPSS (exploitation in 30 days)

2.2% · top 17% of all CVEs (5 Nov 2026)

CISA SSVC

Exploitation: none · Automatable: yes · Technical impact: total

The list uses the assigner's score when there is one, then CISA's, then NVD's: High 8.8.

Weakness

• CWE-125 Out-of-bounds Read (opens in a new tab)All about CWE-125 and its CVEs

Affected products

• ollama · ollama

  • affected < 0.17.1

Affected packages

From reviewed advisories of the GitHub Advisory Database.

• Gogithub.com/ollama/ollamaGHSA-x8qc-fggm-mpqg (opens in a new tab)

What to do

Solution: Upgrade to ollama 0.17.1 or later. The fix in PR #14406 validates that declared tensor offset+size do not exceed the GGUF file size before reading, and adds a length check in the quantizer prior to the unsafe read.

Workaround: Until upgrade is possible: (1) ensure Ollama is bound to a trusted interface only (default OLLAMA_HOST=127.0.0.1); (2) front Ollama with a reverse proxy that requires authentication on /api/create and /api/push; (3) restrict outbound network egress from the Ollama host to prevent exfiltration via /api/push to attacker-controlled registries.

References (3)

• ollama/ollama PR #14406 — ggml: ensure tensor size is valid (fix) (opens in a new tab)patch
• Fix commit 88d57d0 (opens in a new tab)patch
• ollama v0.17.1 release notes (opens in a new tab)release-notes

Sources

The same CVE in the primary databases and aggregators, to check against.

• CVE.org record (opens in a new tab)
• CVE List JSON (GitHub) (opens in a new tab)
• NVD (opens in a new tab)
• FIRST EPSS (opens in a new tab)
• OSV.dev (opens in a new tab)
• GitHub Advisory GHSA-x8qc-fggm-mpqg (opens in a new tab)
• CIRCL Vulnerability-Lookup (opens in a new tab)

Badge for a README or a ticket

[![CVE-2026-7482](https://trackcve.app/badge/CVE-2026-7482.svg)](https://trackcve.app/cve/CVE-2026-7482)

Record last updated 4 May 2026, 13:48 UTC.