Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-85180 – Server-Side Request Forgery (SSRF) – Ollama 0.30.0 through 0.33.2

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-85180 is a Server-Side Request Forgery (SSRF) vulnerability in Ollama, an API server used to run large language models. It affects versions 0.30.0 through 0.33.2 and stems from insufficient validation of redirect destinations when the server pulls tensor-layer model blobs. The flaw is rated High severity (CVSS 8.7) and requires no authentication or user interaction to exploit.

Technical details

  • Root cause: The resolve() function in Ollama’s tensor-layer blob transfer code path does not validate that HTTP redirects stay on the original registry host, unlike the equivalent non-tensor download path.
  • Trigger conditions: An attacker who controls (or spoofs) a model registry can serve a manifest referencing a tensor-layer blob, then respond to the download request with an HTTP redirect (e.g., 301/302/307) pointing to an internal or attacker-chosen host.
  • Attack vector: Network — exploitation occurs via an unauthenticated request to the Ollama server’s model pull functionality (/api/pull), which then follows the malicious redirect.
  • Impact: The Ollama server can be coerced into issuing outbound GET requests to internal network hosts or cloud metadata services (e.g., instance metadata endpoints), potentially exposing sensitive internal data or credentials. Impact is limited to confidentiality; integrity and availability are not affected per the CVSS vector.

Affected software

  • Ollama (ollama/ollama), versions 0.30.0 through 0.33.2 (inclusive)

Severity

  • CVSS v4.0: 8.7 (High) — CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
  • CVSS v3.1: 7.5 (High) — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Mitigation and recommended actions

  • Immediate: No officially confirmed patched release has been identified at the time of writing; monitor the Ollama project for a fix that adds host-allowlist validation to the tensor-layer blob redirect handling (mirroring the fix pattern used for a prior SSRF issue in the non-tensor download path).
  • Workarounds/network mitigations:
    • Restrict outbound network access from hosts running Ollama so they cannot reach internal-only services or cloud metadata endpoints (e.g., block egress to 169.254.169.254 and internal RFC1918 ranges from the Ollama process).
    • Only pull models from trusted, vetted registries; avoid configuring Ollama to pull from untrusted or attacker-controllable registry URLs.
    • Deploy Ollama behind network segmentation so that even if SSRF is triggered, reachable internal targets are minimized.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge