CVE-2025-66960 json
An issue in ollama v.0.12.10 allows a remote attacker to cause a denial of service via the fs/ggml/gguf.go, function readGGUFV1String reads…
published 2026-01-21 9 mo ago modified 2026-06-17 4 mo ago also PYSEC-2026-102 , EUVD-2026-3603
- cvss
- 7.5
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.4%
- EPSS 0.4% chance of exploitation in 30 days, percentile 36%
- public exploits
- 0
- none known
Summary
An issue in ollama v.0.12.10 allows a remote attacker to cause a denial of service via the fs/ggml/gguf.go, function readGGUFV1String reads a string length from untrusted GGUF metadata
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2025-66960 updated cvss 7.5
ollama: ollama: Denial of Service via untrusted GGUF metadata string length
-
Red Hat OpenShift AI (RHOAI) rhoai/odh-trustyai-ragas-lls-provider-dsp-rhel9affected: workaround, no fix planned “Will not fix”
-
Red Hat Ansible Automation Platform 2 ansible-automation-platform/ee-minimal-rhel8, ansible-automation-platform/ee-minimal-rhel9, ansible-automation-platform-26/mcp-tools-rhel9, ansible-automation-platform-24/de-minimal-rhel8, ansible-automation-platform-24/de-minimal-rhel9, ansible-automation-platform-24/ee-minimal-rhel8, +28 morenot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 9 mo ago
Exploit prediction
0.42% chance of exploitation in the next 30 days, higher than 36% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/ollama/ollama/issues/9820 referenced PoC, tagged "exploit" by a source, unverified
- zero.shotlearni.ng https://zero.shotlearni.ng/blog/cve-2025-66960guf-v1-string-length-cause-panic-in-readggufv1string/ referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CISA ADP | 3.1 | 7.5 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H |
| CNA | 3.1 | 7.5 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H |
Classification
References
-
github.com
/ollama/ollama/issues/9820
exploit, issue-tracking, vendor-advisory, report
-
zero.shotlearni.ng
/blog/cve-2025-66960guf-v1-string-length-cause-panic-in-readggufv1string/
exploit, third-party-advisory, evidence
Sources
- CVE List CVE-2025-66960
- NVD CVE-2025-66960
- OSV PYSEC-2026-102
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.