Skip to content
Noroxi
CVE-2026-7482· NVD / CVE Program· CNA Echo

Ollama heap out-of-bounds read in GGUF tensor parsing leaks server process memory to unauthenticated remote attackers

Ollama before 0.17.1 contains a heap out-of-bounds read vulnerability in the GGUF model loader. The /api/create endpoint accepts an attacker-supplied GGUF file in which the declared tensor offset and size exceed the file's actual length; during quantization in fs/ggml/gguf.go and server/quantization.go (WriteTo()), the server reads past the allocated heap buffer. The leaked memory contents may include environment variables, API keys, system prompts, and concurrent users' conversation data, and can be exfiltrated by uploading the resulting model artifact through the /api/push endpoint to an attacker-controlled registry. The /api/create and /api/push endpoints have no authentication in the upstream distribution. Default deployments bind to 127.0.0.1, but the documented OLLAMA_HOST=0.0.0.0 configuration is widely used in practice (large public-internet exposure observed).

HighCVSS 8.8 · v4.0—Proof of concept Fix available
Published
May 4, 2026
Updated
Jun 17, 2026
EPSS
0.7% · 52th percentile
Follow this CVE

Sign in to follow · You’ll be notified if a followed record enters KEV, gets an exploit or is updated.

Report tools

JSON

Action score

35

Monitor

Low priority for now.

CVSS
35 / 40 · 8.8 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.7%

CISA SSVC decision

Exploitation
none
Automatable
yes
Technical impact
total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · Echo
9.1
NVD has not scored this yet; the score shown is the CNA’s.

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Noroxi analysis

No Noroxi analysis for this record yet

We don't hand-write analysis for the hundreds of thousands of vulnerabilities in the database; that wouldn't be honest. For notable, high-impact vulnerabilities our team writes the mechanism, detection and remediation steps.

We use this product, ask for help

Affected systems

VendorProduct
ollamaollama

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

  • ollama ollamabefore 0.17.1

Versions reported by the vendor

Affected version ranges reported by the assigning authority (Echo). Independent of NVD's CPE analysis and usually ahead of it.

  • ollama ollama

    • before 0.17.1affected · semver

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

EcosystemPackageAffected rangeFix
Gogithub.com/ollama/ollamabefore 0.17.10.17.1
openSUSE:Tumbleweedollamabefore 0.33.1-1.10.33.1-1.1

Same product

ollama: all records

Other highest-scoring records for the same primary product.

  • CVE-2024-37032Ollama before 0.1.34 does not validate the format of the digest (sha256 with 64 hex digits) when getting the model path, and thus mishandles
    62This week
  • CVE-2025-63389A critical authentication bypass vulnerability exists in Ollama platform's API endpoints in versions prior to and including v0.12.3.
    39Monitor
  • CVE-2026-103663Path Traversal leading to Remote Code Execution in Ollama
    37Monitor
  • CVE-2026-102697Ollama 0.14.0 before 0.31.2 Experimental Agent Bash Approval Bypass via Prefix-Based Authorization
    34Monitor
  • CVE-2026-85180Ollama 0.30.0 through 0.33.2 SSRF via Cross-Host Tensor Blob Redirect
    34Monitor
  • CVE-2026-65315Ollama Remote Denial of Service via Attacker-Controlled Allocation in GGUF Metadata Parser
    34Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / packageFixed versionSource
ollama ollama0.17.1Vendor (CNA)
Go:github.com/ollama/ollama0.17.1Package registry (OSV)
opensuse:ollama0.33.1-1.1 · openSUSE:TumbleweedPackage registry (OSV)

Exploit status

Proof of concept available

A public proof of concept or detection signature exists. Exploit knowledge is out there; don't delay patching.

Evidence

  • Proof-of-concept repository on GitHub ×3

Noroxi does not host or link to exploit code. Metasploit module names and Nuclei template ids are shown (names, not code); Exploit-DB entries and PoC repositories are given as counts only.

Public exploit evidence
SourceKindDate
Proof-of-concept repository on GitHubstars:62026-05-05
Proof-of-concept repository on GitHubstars:12026-05-07
Proof-of-concept repository on GitHubstars:02026-05-10

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

  1. Published
  2. First PoC+1 d
  3. TodayOct 9, 2026+158 d
EPSS, last 120 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

  • CVE-2026-575753 days apartThere exists an unauthenticated remote information disclosure vulnerability in Ollama's model quantization engine
    30Monitor
  • CVE-2024-12055410 days apartDoS using malicious gguf model file in ollama/ollama
    30Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

Technical details

Attack conditions

  • Anyone who can reach it over the internet can trigger it.
  • No account or password is required.
  • No user action is required.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
Integrity
Availability
Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
X

Weakness class (CWE)

CWE-125 · Out-of-bounds Read

CVSS vector

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:Y/R:A/V:D/RE:L/U:Red

nvd-secondary

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

ATT&CK techniques

—

Change log

  1. Fix✗ → ✓

For records you follow, these changes also arrive as notifications. →

References

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records