LiveActive security incident?Get immediate response
CVE Record

CVE-2025-15514: Ollama Multi-Modal Model Image Processing NULL Pointer Dereference

Ollama 0.11.5-rc0 through current version 0.13.5 contain a null pointer dereference vulnerability in the multi-modal model image processing functionality. When processing base64-encoded image data via the /api/chat endpoint, the application fails to validate that the decoded data represents valid media before passing it to the mtmd_helper_bitmap_init_from_buf function. This function can return NULL for malformed input, but the code does not check this return value before dereferencing the pointer in subsequent operations. A remote attacker can exploit this by sending specially crafted base64 image data that decodes to invalid media, causing a segmentation fault and crashing the runner process. This results in a denial of service condition where the model becomes unavailable to all users until the service is restarted.

HighCVSS 8.7Not KEV-listedUpdated
Discuss exposureBack to CVEs
Glexia's TakeAutomated analysishigh

Security readout for executives and security teams

Plain-English summary

Ollama can be remotely crashed when malformed base64 image data is sent to its chat API for multi-modal processing. The impact is availability: the runner process segfaults and the model becomes unavailable until restart. The bundle does not show active exploitation.

Executive priority

Prioritize remediation for exposed Ollama services because a single unauthenticated request can make models unavailable. Treat internal-only deployments as lower urgency but still patchable operational risk, especially where shared AI services support business workflows.

Technical view

CVE-2025-15514 is a NULL pointer dereference in Ollama image handling. The decoded image buffer is not validated before mtmd_helper_bitmap_init_from_buf; when that returns NULL, later code dereferences it and crashes. The bundle reports Ollama 0.11.5-rc0 through 0.13.5 and CVSS 4.0 score 8.7.

Likely exposure

Exposure is most relevant where Ollama’s /api/chat endpoint is reachable over a network and accepts multi-modal image inputs. Internet-facing, shared, or unauthenticated deployments have higher operational risk. The source bundle lists Ollama only; no downstream affected products are established here.

Exploitation context

The CVSS vector indicates remote, low-complexity, unauthenticated exploitation with no user interaction and high availability impact. The provided references include a technical/exploit-tagged Huntr report, but the bundle says KEV is false and provides no evidence of active exploitation.

Researcher notes

Evidence supports an availability-only denial of service in multi-modal image processing. Confidentiality and integrity impacts are listed as none. Fix availability is not established in the bundle, so avoid claiming a patched version without vendor confirmation.

Mitigation direction

  • Check Ollama vendor guidance for a fixed release or official workaround.
  • Restrict network access to Ollama APIs, especially /api/chat.
  • Require authentication or trusted network placement for model endpoints.
  • Disable or limit multi-modal image processing where operationally feasible.
  • Restart affected runner processes after a crash while remediation is pending.

Validation and detection

  • Inventory Ollama versions and identify 0.11.5-rc0 through 0.13.5 deployments.
  • Confirm whether /api/chat is reachable from untrusted networks.
  • Review logs for runner segmentation faults during image chat requests.
  • Verify compensating controls restrict untrusted image submissions.
  • Track Red Hat and Ollama advisory updates for remediation status.
Prepared
Confidence
medium
Sources
8

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 · low confidence lookup

CWE-395: Exact CWE lookup

Use the exact CWE identifier as the starting point before reviewing related ATT&CK behavior. 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
cve · low confidence lookup

CVE-2025-15514 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
High
CVSS
8.7 (4.0)
Known Exploited
No
Published

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

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.

2CVSS vectors
5Timeline events
2ADP providers
7Source links

SSVC decision data

CISA-ADPCISA Coordinator
Timestamp
Version
2.0.3
Exploitation: pocAutomatable: yesTechnical Impact: partial

CVSS vector scores

2 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
8.7CVSS 4.0HighCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N——VulnCheck
7.5CVSS 3.1HighCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H3.93.6redhat-SADP

Vulnerability scoring details

Base CVSS 4.0 score

8.7High
CVSS 4.0 vector shape for CVE-2025-15514Attack VectorAttack ComplexityAttack RequirementsPrivileges RequiredUser InteractionVS ConfidentialityVS IntegrityVS AvailabilitySS ConfidentialitySS IntegritySS Availability

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

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. CVE reservedCVE Program

    The CVE ID was reserved by the assigning CNA.

  2. ADP timelineredhat-SADP

    Made public.

  3. CVE publishedCVE Program

    The CVE record was published.

  4. ADP timelineredhat-SADP

    Reported to Red Hat.

  5. CVE updatedCVE Program

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

ADP provider summaries

CISA-ADPCISA ADP Vulnrichment
other:ssvc
redhat-SADPOllama: Ollama: Denial of Service via malformed image processing
other:Red Hat severity ratingcvssV3_1
  • 2026-01-13T00:09:32.095Z: Reported to Red Hat.
  • 2026-01-12T23:03:52.922Z: Made public.

Source materials

Affected products

Products and packages named in the record

VendorProductVersion / packageStatus
OllamaOllamav0.11.5-rc0unknown
Weakness

CWE details

CWE-395

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

CWE-395 · source CWE mapping

Use of NullPointerException Catch to Detect NULL Pointer Dereference

Use of NullPointerException Catch to Detect NULL Pointer Dereference represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.

Open CWE intelligenceSame-CWE CVEs