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

4,331

AI/ML CVEs Tracked

535

Critical

108

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 2900 results — no patch

SeverityCVE IDSummaryCVSSEPSSPackageDate

MEDICVE-2025-13327uv: ZIP parsing differential allows code execution6.30.2%rhaiis-preview/vllm-cuda-rhel9Feb 27 CRITECVE-2026-27966langflow: Code Injection enables RCE9.835.2%langflowFeb 26 MEDICVE-2026-27578n8n: XSS enables session hijacking5.40.2%n8nFeb 25 CRITECVE-2026-27577n8n: Code Injection enables RCE9.910.7%n8nFeb 25 HIGHCVE-2026-27498n8n: Code Injection enables RCE8.80.8%n8nFeb 25 HIGHCVE-2026-27497n8n: SQL Injection exposes database8.80.9%n8nFeb 25 CRITCVE-2026-27495n8n: Code Injection enables RCE9.90.8%n8nFeb 25 CRITCVE-2026-27494n8n: security flaw enables exploitation9.90.4%n8nFeb 25 CRITCVE-2026-27493n8n: Code Injection enables RCE9.01.4%n8nFeb 25 HIGHCVE-2026-27795LangChain: SSRF allows internal network access7.40.2%—Feb 25 HIGHCVE-2026-2492TensorFlow: security flaw enables exploitation7.80.3%—Feb 20 HIGHCVE-2026-27001OpenClaw: prompt injection via unsanitized workspace path7.80.2%openclawFeb 20 MEDICVE-2026-26972OpenClaw: path traversal allows arbitrary file write6.70.2%openclawFeb 20 HIGHCVE-2026-26321OpenClaw: path traversal enables local file exfiltration7.50.5%openclawFeb 19 MEDICVE-2026-26320OpenClaw: UI deception enables arbitrary command execution6.50.5%openclawFeb 19 HIGHECVE-2026-26286sillytavern: SSRF allows internal network access8.50.3%—Feb 19 LOWECVE-2026-24764OpenClaw: indirect prompt injection via Slack metadata3.70.2%openclawFeb 19 MEDICVE-2025-12343ffmpeg: security flaw enables exploitation5.50.2%—Feb 18 CRITECVE-2026-2654smolagents: SSRF allows internal network access9.80.4%smolagentsFeb 18 CRITCVE-2025-14014Smart Panel: unauthenticated file upload enables RCE9.80.4%Smart PanelFeb 12

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