Database/AI/ML frameworks & serving
Ollama: model pull follows cross-host redirects, giving SSRF to internal and metadata endpoints
Impact
When pulling tensor-layer models, Ollama does not validate the destination of a redirect, so a registry the server is pointed at can steer blob downloads to any host the server can reach. The advisory calls out cloud metadata endpoints explicitly: on a GPU node, 169.254.169.254 usually hands back the instance service-account token, which is what makes this more than a curiosity - a model pull turns into credential disclosure for whatever role the node carries, and on a shared cluster that role often reaches object storage holding other tenants' datasets and checkpoints. VulnCheck lists 0.30.0 through 0.33.2 as affected. Impact is read/exfiltration of responses, not code execution.
Who can reach it
Unauthenticated with respect to Ollama itself: whoever controls the registry or the manifest being pulled. That includes anyone who can get your operators to pull a model from a hostile registry, and - where the Ollama API is exposed to tenants or to a notebook network - any caller who can issue a pull request to it. No credentials on the Ollama side are needed.
What to do
The record points to an open upstream issue and does not name a fixed release, so treat this as mitigate-only for now: block egress from inference nodes to link-local and internal address ranges, require IMDSv2 with a hop limit of 1 (or the equivalent metadata hardening on your cloud), restrict model pulls to registries you control, and keep the Ollama API off any network a tenant can reach. All of that is config and network policy - no node drain or reboot. Re-check the upstream issue for a fixed version before relying on the mitigations long term.
References
Related entries
- Gradio (`/queue/join`): SSRFCVE-2024-4325 · Gradio (`/queue/join`)High
- ONNX: Security-control bypass through 1.20.1CVE-2026-28500 · ONNXHigh
- ONNX (`ExternalDataInfo`): Security control bypass in external-data path handlingCVE-2026-34445 · ONNX (`ExternalDataInfo`)High
- JupyterLab: saved HTML cell output can run arbitrary JupyterLab commands on one user clickCVE-2026-42557 · JupyterLab (HTML sanitizer / CommandLinker command dispatch)High
- LocalAI (`/models/apply`): Unauthenticated SSRF fetching arbitrary internal URLsCVE-2026-59707 · LocalAI (`/models/apply`)High
- Text Generation Inference (TGI): SSRF in the OpenAI-compatible multimodal chat endpointCVE-2026-63086 · Text Generation Inference (TGI)High
This entry is curated: imported from vendor advisories with machine assistance, not yet individually verified. Confirm against your vendor's advisory before acting, and report anything wrong.