Ollama Vulnerabilities

pipLLM Inference

AI Threat Alert tracks 41 known vulnerabilities in Ollama, 6 rated critical — an AI/ML llm inference in the pip ecosystem. Each CVE includes CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis.

84
Risk Score
41
Total CVEs
6
Critical
pip
Ecosystem
Oct 27, 2026
Last CVE
19%
Patch Rate
36d
Avg Time to Patch
186,993 stars19,088 forks4,656 issues1,888 dependentsLast push Nov 14, 2026
View on GitHub

Known Vulnerabilities(41 total, page 1 of 2)

SeverityCVE IDSummaryCVSSPublished
MEDIUMCVE-2026-116608VideoLLaMA2: unverified model integrity on load5.4Oct 27, 2026HIGHCVE-2026-115586virtualenv: bash prompt injection allows command execution--Oct 23, 2026HIGHCVE-2026-111702ChatOllama: IDOR exposes other users' knowledge bases7.5Oct 16, 2026HIGHCVE-2026-108836Ollama: SSRF via model name validation in Pull API7.3Oct 12, 2026MEDIUMCVE-2026-103663Ollama: path traversal in /api/pull enables root RCE--Oct 8, 2026HIGHCVE-2026-102697Ollama: agent Bash approval bypass via shell operators7.8Sep 29, 2026HIGHGHSA-456v-xq2p-r4cjcode-ollama: shell injection in grep_search allows RCE7.8Sep 28, 2026HIGHCVE-2026-566769router: DNS rebinding SSRF in image prefetch7.4Sep 23, 2026HIGHCVE-2026-58197ToolHive: default network profile enables MCP lateral movement8.8Sep 18, 2026HIGHCVE-2026-59158nuxt-ollama: API key leaked in public SSR payload7.5Sep 9, 2026MEDIUMCVE-2026-86289Ollama: integer overflow in GGUF decoder causes DoS4.3Sep 7, 2026HIGHCVE-2026-85180Ollama: SSRF via unvalidated model-pull redirects7.5Sep 3, 2026HIGHCVE-2026-65315Ollama: crafted GGUF file crashes inference server7.5Jul 21, 2026UNKNOWNCVE-2026-15685Ollama: downloadBlob array index bug enables unauth DoS--Jul 13, 2026HIGHCVE-2026-5757Ollama: unauthenticated heap memory disclosure7.5Jun 26, 2026CRITICALCVE-2026-463399router: unauthenticated RCE exposes LLM API keys10.0May 19, 2026MEDIUMCVE-2026-43979local-deep-research: HTML injection enables SSRF via WeasyPrint5.0May 11, 2026CRITICALCVE-2026-44007vm2: sandbox escape via nesting:true enables RCE9.1May 7, 2026CRITICALCVE-2026-7482Ollama: heap OOB read leaks API keys and chat data9.1May 4, 2026CRITICALCVE-2026-42249Ollama: path traversal + unsigned update = silent RCE9.8Apr 29, 2026CRITICALCVE-2026-42248Ollama: silent auto-update bypasses signature check on Windows9.8Apr 29, 2026LOWCVE-2026-7020Ollama: path traversal in tensor model transfer handler3.7Apr 26, 2026HIGHCVE-2025-66960ollama: Input Validation flaw enables exploitation7.5Jan 21, 2026HIGHCVE-2025-66959ollama: Input Validation flaw enables exploitation7.5Jan 21, 2026HIGHCVE-2025-15514ollama: security flaw enables exploitation7.5Jan 12, 2026

Showing 1–25 of 41

Frequently asked questions

What is Ollama?

Ollama is an AI/ML llm inference tracked by AI Threat Alert for security vulnerabilities in the pip ecosystem.

How many known vulnerabilities does Ollama have?

Ollama has 41 known CVEs, 6 of them critical, tracked from NVD and GitHub Advisory.

Which ecosystem is Ollama distributed in?

Ollama is distributed via the pip ecosystem and categorized as llm inference.

Where does the Ollama vulnerability data come from?

Vulnerability data is sourced from NVD and GitHub Advisory, enriched with CVSS, EPSS, exploit signals, and patch status for each CVE.

How do I assess the risk of Ollama?

Review each CVE below — every entry shows CVSS severity, EPSS exploit probability, exploitation signals, and whether a patched version is available.

Monitor Ollama in your stack

Get instant alerts when new vulnerabilities affect Ollama. CISO analysis, ATLAS technique mappings, and compliance reports included.

Start Monitoring