AI Security Threat Feed

Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.

Sources

Each CVE is enriched with

CVSS severity
EPSS exploit probability
Exploitation confidence
AI-component classification
Compliance mappings

4,307

AI/ML CVEs Tracked

533

Critical

New This Week

In CISA KEV

Sort:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 25 results — KEV only, Active exploitation

SeverityCVE IDSummaryCVSSEPSSPackageDate

CRITCVE-2026-94127F5 BIG-IP APM: unauthenticated RCE via OAuth server9.826.6%—Sep 22 CRITCVE-2026-64849MLflow: unauth SSRF via webhook hits cloud metadata9.310.0%mlflowAug 17 CRITCVE-2026-9198Langflow: token forgery + exec() chain to RCE9.828.7%Langflow OSSJul 17 HIGHCVE-2026-59822LiteLLM: MCP auth bypass via fabricated OAuth header8.20.8%litellmJul 8 CRITCVE-2026-55255Langflow: IDOR allows cross-user flow execution9.90.9%langflowJun 19 HIGHCVE-2026-42271LiteLLM: RCE via MCP test endpoint command injection8.891.4%litellmMay 8 CRITCVE-2026-42208LiteLLM: SQL injection exposes LLM API credentials9.889.4%litellmMay 8 CRITCVE-2026-33017langflow: Code Injection enables RCE9.896.2%langflowMar 20 HIGHCVE-2026-0770langflow: security flaw enables exploitation—62.6%langflowJan 23 CRITCVE-2026-21858n8n: Input Validation flaw enables exploitation10.078.2%n8nJan 8 HIGHCVE-2025-68613n8n: security flaw enables exploitation8.899.0%n8nDec 19 HIGHCVE-2025-34291langflow: security flaw enables exploitation8.893.2%langflowDec 5 CRITCVE-2025-62593ray: Code Injection enables RCE—60.2%rayNov 26 CRITCVE-2025-3248Langflow: Unauth RCE via code injection endpoint9.8100.0%langflowApr 7 CRITCVE-2024-51567CyberPanel: pre-auth RCE via secMiddleware bypass10.084.4%—Oct 29 CRITCVE-2024-51378CyberPanel: auth bypass enables unauthenticated RCE10.094.7%—Oct 29 HIGHCVE-2024-6587LiteLLM: SSRF leaks OpenAI API key to attacker7.534.4%litellmSep 13 HIGHCVE-2024-4325Gradio: SSRF exposes internal network and cloud metadata8.637.1%gradioJun 6 HIGHCVE-2024-37032Ollama: path traversal enables RCE via model blob API8.889.6%ollamaMay 31 UNKNCVE-2024-1561Gradio: path traversal enables arbitrary file read—9.3%gradioApr 16

Frequently asked questions

What is an AI security threat feed?

An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.

Which sources are the AI CVEs tracked from?

CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.

What AI systems do these vulnerabilities affect?

Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.

How often is the AI threat feed updated?

The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.

Is the AI security feed free?

Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.

Need deeper analysis?

Get ATLAS technique mappings, compliance reports (ISO 42001, EU AI Act), breaking alerts, and full CISO analysis with a Pro subscription.

Start 14-Day Free Trial