# CVE-2026-85180: Ollama unvalidated redirect in model blob downloads

Source: https://junglewise.ai/threats/cve-2026-85180-ollama-unvalidated-redirect-in-model-blob-downloads  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-03. Updated: 2026-09-25  
License: CC BY 4.0 with a link back

CVE-2026-85180 · Severity: high · CVSS 7.5 · Published 2026-09-03

Ollama, an open-source tool for running AI models locally, fails to validate redirect destinations when downloading model files. An attacker controlling a malicious model registry can trick Ollama servers into making requests to internal hosts, including cloud metadata endpoints, potentially exposing sensitive credentials or information used to run the service.

Technologies: [Ollama](https://junglewise.ai/threats/technologies/ollama). Vendors: [Ollama](https://junglewise.ai/threats/vendors/ollama).

## Quick answers

**Is CVE-2026-85180 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-85180 being exploited in the wild.

**How severe is CVE-2026-85180?** High severity, with a CVSS score of 7.5, published 3 September 2026.

**Which products and versions are affected?** Ollama prior to patch.

**Is there a fix for CVE-2026-85180?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2026-85180 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-85180?** Check whether you run 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.

## Technical details

The vulnerability exists in the blob download logic (x/transfer/download.go) where HTTP redirects are not validated for safety. When pulling tensor-layer models, if a registry serves a specially crafted manifest with redirect responses, the client will follow those redirects to arbitrary hosts without verifying the destination. An unauthenticated attacker who controls or compromises a model registry can exploit this to perform server-side request forgery (SSRF), causing the Ollama server to issue GET requests to internal or cloud metadata endpoints. The attack requires the victim to pull a model from a malicious registry but does not require authentication to the registry itself.

## Affected products

- Ollama Ollama prior to patch

## Timeline

- 2026-09-03: disclosed

## References

- [https://github.com/ollama/ollama](https://github.com/ollama/ollama)
- [https://github.com/ollama/ollama/blob/v0.33.2/x/transfer/download.go](https://github.com/ollama/ollama/blob/v0.33.2/x/transfer/download.go)

## Related threats

- [Ollama server-side request forgery in Pull API](https://junglewise.ai/threats/cve-2026-108836-a-vulnerability-has-been-found-in-ollama-up-to-0-34-1-the)
- [Ollama authorization bypass in experimental agent Bash tool approval](https://junglewise.ai/threats/cve-2026-102697-ollama-versions-0-14-0-before-0-31-2-contain-an-incorrect)
- [Ollama integer overflow in GGUF decoder](https://junglewise.ai/threats/cve-2026-86289-ollama-integer-overflow-in-gguf-decoder)
- [Ollama uncontrolled memory allocation in GGUF metadata parser](https://junglewise.ai/threats/cve-2026-65315-ollama-uncontrolled-memory-allocation-in-gguf-metadata-parser)
- [Ollama downloadBlob improper validation of array index denial of service](https://junglewise.ai/threats/cve-2026-15685-ollama-downloadblob-improper-validation-of-array-index-denial-of)