Quick answers
- Is CVE-2026-7482 exploited in the wild?
- No. Junglewise Threat Intelligence has no report of CVE-2026-7482 being exploited in the wild.
- How severe is CVE-2026-7482?
- Critical severity, with a CVSS score of 9.1, published 4 May 2026.
- Which products and versions are affected?
- github.com/ollama/ollama (Go) SEMVER:introduced=0,fixed=0.17.1.
- Is there a fix for CVE-2026-7482?
- Yes. github.com/ollama/ollama (Go): upgrade to 0.17.1 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
- How is CVE-2026-7482 attacked?
- It is attacked over the network, in a network appliance.
- Am I affected by CVE-2026-7482?
- Check whether you run github.com/ollama/ollama (Go) or Ollama at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.
How to fix
- github.com/ollama/ollama (Go): upgrade to 0.17.1 or later
go get github.com/ollama/ollama@v0.17.1
Technical details
A heap out-of-bounds read exists in Ollama's GGUF model loader within fs/ggml/gguf.go and server/quantization.go. The vulnerability is triggered via the /api/create endpoint when a user supplies a GGUF file with tensor offset and size values that exceed the actual file length. During the quantization process (WriteTo()), the server reads past the allocated heap buffer. An attacker can exfiltrate the leaked memory—which may contain API keys, environment variables, and concurrent user data—by using the /api/push endpoint to send the resulting model to an attacker-controlled registry. These endpoints are unauthenticated in default upstream distributions.
Affected products
- Ollama Ollama before 0.17.1
Identifiers
- CVE-2026-7482
- GHSA-x8qc-fggm-mpqg
- GO-2026-5748
Timeline
- 2026-02-24: patched: Release v0.17.1 published
- 2026-02-25: other: Fix merged into main branch
- 2026-05-04: advisory: CVE-2026-7482 published