CVE-2025-66959
Published: 21 January 2026
Summary
CVE-2025-66959 is a high-severity Improper Input Validation (CWE-20) vulnerability in Ollama Ollama. Its CVSS base score is 7.5 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Application or System Exploitation (T1499.004); ranked in the top 29.4% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as NLP and Transformers; in the Data-Related Vulnerabilities risk domain.
The strongest mitigations our analysis identified are NIST 800-53 SC-5 (Denial-of-service Protection) and SI-10 (Information Input Validation).
Deeper analysis
CVE-2025-66959 is a denial-of-service vulnerability in Ollama version 0.12.10, published on 2026-01-21. The flaw exists in the GGUF decoder and is classified under CWE-20 (Improper Input Validation) and CWE-400 (Uncontrolled Resource Consumption). It carries a CVSS v3.1 base score of 7.5 (AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H), indicating high severity due to its potential for significant availability impact.
A remote, unauthenticated attacker can exploit the vulnerability over the network with low attack complexity and no user interaction required. By crafting malicious input targeting the GGUF decoder, the attacker triggers a denial of service, such as a panic or crash, disrupting service availability without compromising confidentiality or integrity.
Mitigation details are available in the referenced advisories, including the Ollama GitHub issue at https://github.com/ollama/ollama/issues/9820 and the technical analysis at https://zero.shotlearni.ng/blog/cve-2025-66959panic-dos-via-unchecked-length-in-gguf-decoder-copy/. Security practitioners should consult these for patch information and recommended updates.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-3626
Vulnerability details
An issue in ollama v.0.12.10 allows a remote attacker to cause a denial of service via the GGUF decoder
- CWE(s)
AI Security AnalysisAI
- AI Category
- NLP and Transformers
- Risk Domain
- Data-Related Vulnerabilities
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: ollama
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Remote exploitation of input validation flaw in GGUF decoder directly enables application/system crash for denial of service (T1499.004).
CVEs Like This One
Affected Assets
Mitigating Controls
Mitigating Controls (NIST 800-53 r5) AI
SI-10 requires validating inputs to the GGUF decoder, directly addressing the improper input validation (CWE-20) that enables the DoS crash.
SC-5 provides denial-of-service protection mechanisms to mitigate uncontrolled resource consumption (CWE-400) from malicious GGUF inputs causing service crashes.
SI-2 ensures timely flaw remediation by applying patches for the known GGUF decoder vulnerability in Ollama v0.12.10.