cve.bz

CVE-2026-7482 (Bleeding Llama) ollama ollama: Out-of-bounds Read

8.8 highEPSS 7.1%Fix available

Known as Bleeding Llama

High (8.8) in ollama ollama. EPSS 7.1% estimated probability of exploitation activity in the next 30 days. Fixed in github.com/ollama/ollama 0.17.1.

On this page
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).

Severity

CVSS 4.0

8.8 high
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/AU:Y/R:A/V:D/RE:L/U:Red

CVSS 3.1

9.1 critical
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:H
EPSS
7.1% (unchanged from 7.1% a week ago; 0.7% 30 days ago) estimated probability of exploitation activity in the next 30 days; 94th percentile. Scored 2026-11-21. A forecast for this CVE across the internet, not for your own systems.
CISA's assessment (SSVC)
Exploitation: none · Automatable: yes · Technical impact: total, assessed 2026-05-04. From CISA's Vulnrichment in the CVE List: whether it is exploited, whether exploiting it can be automated, and how much control it gives.
CWE
CWE-125 Out-of-bounds Read
Published
Modified
NVD analysis
Analyzed
Record from
the NVD, synced

Fix and patched versions

Ask an AI about this CVE

Show the promptExplain CVE-2026-7482 for an engineer deciding whether to act. Use https://cve.bz/api/public/cves/CVE-2026-7482?via=ask-ai-copy and https://cve.bz/cve/CVE-2026-7482?via=ask-ai-copy as the source of truth: what is affected and which versions fix it, whether it is in CISA KEV, public exploits, and its EPSS (an internet-wide 30-day estimate of exploitation activity, not a forecast for my systems). If they give no fixed versions, use the CVE record https://cveawg.mitre.org/api/cve/CVE-2026-7482 or the vendor advisory, not third-party mirrors. Tell me how to check whether I am affected and how to verify a fix. Cite the sources and say where they are uncertain.

Opens a third-party assistant; its answer is its own, not cve.bz's. The prompt holds only this CVE's id and public links.

Affected

Versions

From the CNA's record in the CVE List.

ProductAffected
ollamabefore 0.17.1

Packages (OSV)

AdvisoryEcosystemPackageAffectedFixed in
GHSA-x8qc-fggm-mpqgGogithub.com/ollama/ollama<0.17.10.17.1
GO-2026-5748Gogithub.com/ollama/ollama<0.17.10.17.1

Linux distributions

DistributionReleasePackageFixed inAdvisory
SUSELinux Enterprise Server 16.0, Linux Enterprise Server for SAP applications 16.0govulncheck-vulndb0.0.20260727T201416-160000.1.1SUSE-SU-2026:23216-1 SUSE-SU-2026:23227-1
openSUSELeap 16.0govulncheck-vulndb0.0.20260727T201416-160000.1.1openSUSE-SU-2026:21551-1
openSUSETumbleweedollama0.33.1-1.1openSUSE-SU-2026:11688-1

From the distributions' data via OSV.dev: SUSE security data, CC BY 4.0. Modified: reformatted and linked to CVE records. Credits. On the distributions' own pages: SUSE · openSUSE.

Red Hat

Red Hat rates this Critical.

Red Hat's statement

An Important information disclosure flaw exists in Ollama, allowing a remote, unauthenticated attacker to read heap memory via a crafted GGUF file submitted to the /api/create endpoint. This can expose sensitive data, including API keys and user conversation data, which can then be exfiltrated. While default deployments bind to localhost, configurations exposing Ollama to the public internet significantly increase the risk.

In this flaw a network attacker may leak sensitive data (C:H, I:N) with limited scope of system denial of servci (A:L), where a system reboot may not be the scenario.

ProductPackageStateAdvisory
Migration Toolkit for Applications 8mta/mta-solution-server-rhel9Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-24/lightspeed-rhel8Not affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-25/lightspeed-rhel8Not affected
Red Hat build of Debezium 3debezium-ai-embeddings-ollamaNot affected
Red Hat build of Debezium 3langchain4j-ollamaNot affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9Not affected
Red Hat Trusted Profile Analyzerrhtpa/rhtpa-trustification-service-rhel9Not affected

Contains Red Hat Security Data © Red Hat, Inc., licensed under CC BY 4.0. Source: https://access.redhat.com/security/data. Modified: reformatted. Red Hat's page for CVE-2026-7482.

GitHub PoC

Repositories on GitHub named after this CVE or listed for it by the PoC-in-GitHub index. For those marked Harbor Check: matches CVE, Flawharbor read the code and found it implements this CVE's exploitation technique: read, not run, and its dependencies only checked for warning signs, so a pointer and no guarantee. The rest are unverified: some hold a working proof of concept, some nothing useful, and some malware made to look like one. Read the code before you run any of it. How Harbor Check reads them, and what it found.

Detection rules

Ways to detect this CVE, not exploit code: the nuclei template that checks a system for it, and the Suricata and Snort rules that name it. A rule set may ship a rule turned off, so check yours by its sid.

Attack patterns (CAPEC)

  • CAPEC-540 Overread Buffers Likelihood: Low · Severity: High

The attack patterns MITRE's CAPEC relates to this record's weaknesses, as MITRE names them. Credits.

References

Check your stackJSON