LiveActive security incident?Get immediate response
CVE Record

CVE-2026-5530: Ollama Model Pull API download.go server-side request forgery

A flaw has been found in Ollama up to 0.18.1. This issue affects some unknown processing of the file server/download.go of the component Model Pull API. Executing a manipulation can lead to server-side request forgery. The attack can be launched remotely. The vendor was contacted early about this disclosure but did not respond in any way.

MediumCVSS 6.5Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysismoderate

Security readout for executives and security teams

Plain-English summary

CVE-2026-5530 is a reported server-side request forgery issue in Ollama's Model Pull API. If reachable, the API could be abused to make the Ollama server send unintended requests. Treat this as a moderate infrastructure risk, especially where Ollama hosts can reach internal services or sensitive metadata endpoints.

Executive priority

Prioritize assessment where Ollama supports production workflows or has broad internal network reach. This is not described as actively exploited in the provided sources, but SSRF can become serious when infrastructure trust boundaries are weak.

Technical view

The bundle identifies CWE-918 in Ollama server/download.go affecting Model Pull API processing. Listed affected versions are Ollama 0.18.0 and 0.18.1, with the description saying up to 0.18.1. CVSS v2 is 6.5 with network access, low complexity, single authentication, and partial confidentiality, integrity, and availability impact.

Likely exposure

Exposure is most likely where Ollama 0.18.0 or 0.18.1 is deployed and the Model Pull API is reachable by users or services. Risk increases if the host can reach internal networks, cloud metadata services, or administrative endpoints.

Exploitation context

The provided bundle does not show CISA KEV listing or cite confirmed active exploitation. VulDB states the issue is remotely launchable and that the vendor did not respond. The bundle does not provide patch details, exploit maturity, or safe reproduction details.

Researcher notes

Evidence is thin and largely third-party. The sources identify SSRF in server/download.go but do not include vendor confirmation, root-cause detail, patch commits, or safe detection logic. Avoid assuming broader version impact beyond the provided affected list without additional vendor evidence.

Mitigation direction

  • Inventory Ollama deployments and identify versions 0.18.0 and 0.18.1.
  • Restrict Model Pull API access to trusted networks and authenticated users.
  • Limit outbound network access from Ollama hosts to required destinations.
  • Check Ollama vendor guidance for fixed versions or official mitigations.
  • Monitor Ollama logs for unusual model pull activity.
  • Review VulDB CTI indicators if you have authorized access.

Validation and detection

  • Confirm installed Ollama versions across servers, containers, and developer workstations.
  • Map where the Model Pull API is exposed internally or externally.
  • Review network egress logs from Ollama hosts for unexpected destinations.
  • Check access controls protecting Ollama API endpoints.
  • Verify host segmentation limits access to sensitive internal services.
  • Track the CVE record and vendor channels for updated remediation guidance.
Prepared
Confidence
medium
Sources
6

Public sources used

Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.

Potential ATT&CK relevance

Conservative CVE-to-ATT&CK context

These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.

ATT&CK lookup starting points

Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.

cwe · medium confidence lookup

CWE-918: Information exposure and cloud metadata lookup

Information exposure and SSRF weaknesses can make discovery, cloud metadata, and credential material review relevant. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.

Open ATT&CK lookup
description · low confidence lookup

Cloud metadata behavior lookup

The CVE wording references SSRF or metadata access, so cloud discovery and credential material review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.

Open ATT&CK lookup
cve · low confidence lookup

CVE-2026-5530 mapping review

Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.

Open ATT&CK lookup
Vulnerability profileCVE Program record
Severity
Medium
CVSS
6.5 (2.0)
Known Exploited
No
Published

Vector: AV:N/AC:L/Au:S/C:P/I:P/A:P/E:ND/RL:ND/RC:UR

Official CVE source material

CNA and ADP enrichment extracted from CVE v5

These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.

4CVSS vectors
6Timeline events
1ADP providers
5Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: noneAutomatable: noTechnical Impact: partial

CVSS vector scores

4 official scores

We collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.

ScoreVersionSeverityVectorExploitImpactSource
6.5CVSS 2.0MediumAV:N/AC:L/Au:S/C:P/I:P/A:P/E:ND/RL:ND/RC:UR86.4VulDB
6.3CVSS 3.1MediumCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:X/RL:X/RC:R2.83.4VulDB
6.3CVSS 3.0MediumCVSS:3.0/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L/E:X/RL:X/RC:R2.83.4VulDB
5.3CVSS 4.0MediumCVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X——VulDB

Vulnerability scoring details

Base CVSS 4.0 score

5.3Medium
CVSS 4.0 vector shape for CVE-2026-5530Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:X

Attack Vector
NetworkAdjacentLocalPhysical
Attack Complexity
LowHigh
Attack Requirements
NonePresent
Privileges Required
NoneLowHigh
User Interaction
NonePassiveActive
VS Confidentiality
HighLowNone
VS Integrity
HighLowNone
VS Availability
HighLowNone
SS Confidentiality
HighLowNone
SS Integrity
HighLowNone
SS Availability
HighLowNone

Vulnerability timeline

Timeline events are normalized from CVE metadata, CNA source timelines, ADP timelines, and KEV metadata when present.

  1. Source timelineVulDB

    Advisory disclosed

  2. Source timelineVulDB

    VulDB entry created

  3. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  4. CVE publishedCVE Program

    The CVE record was published.

  5. CVE updatedCVE Program

    The CVE record metadata indicates this as the latest update time.

  6. Source timelineVulDB

    VulDB entry last update

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
n/aOllama0.18.0, 0.18.1Listed
Weakness

CWE details

CWE-918

CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.