AI Threat Alert

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
3,023

AI/ML CVEs Tracked

424

Critical

115

New This Week

19

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 3023 results
Severity CVE ID Summary CVSS EPSS Package Date
MEDI CVE-2026-26019 langchain_community: SSRF allows internal network access 4.1 0.4% langchain_community Feb 11 LOW CVE-2026-26013 langchain-core: SSRF allows internal network access 3.7 0.4% langchain_core Feb 10 MEDI CVE-2025-14831 GnuTLS: TLS cert parsing DoS hits vllm inference 5.3 0.6% rhaiis/vllm-cuda-rhel9 Feb 9 MEDI CVE-2026-25631 n8n: Input Validation flaw enables exploitation 6.5 0.3% n8n Feb 6 CRIT CVE-2026-25592 semantic-kernel: Path Traversal enables file access 9.9 2.4% semantic-kernel Feb 6 HIGH E CVE-2026-25580 pydantic-ai: SSRF allows internal network access 8.6 0.6% pydantic-ai-slim Feb 6 MEDI CVE-2026-25640 pydantic-ai: Path Traversal enables file access 5.4 0.3% pydantic-ai-slim Feb 6 MEDI E CVE-2026-25475 OpenClaw: path traversal enables arbitrary file read 6.5 0.7% openclaw Feb 4 HIGH CVE-2026-21893 n8n: Input Validation flaw enables exploitation 7.2 1.3% n8n Feb 4 CRIT CVE-2026-25115 n8n: Protection Bypass circumvents security controls 9.9 0.5% n8n Feb 4 HIGH CVE-2026-25056 n8n: Arbitrary File Upload enables RCE 8.8 0.7% n8n Feb 4 HIGH CVE-2026-25055 n8n: Path Traversal enables file access 8.1 1.7% n8n Feb 4 MEDI CVE-2026-25054 n8n: XSS enables session hijacking 5.4 0.2% n8n Feb 4 CRIT CVE-2026-25053 n8n: Command Injection enables RCE 9.9 0.6% n8n Feb 4 CRIT CVE-2026-25052 n8n: security flaw enables exploitation 9.9 0.3% n8n Feb 4 MEDI CVE-2026-25051 n8n: XSS enables session hijacking 5.4 0.2% n8n Feb 4 CRIT CVE-2026-25049 n8n: security flaw enables exploitation 9.9 1.4% n8n Feb 4 HIGH CVE-2025-61917 n8n: Info Disclosure leaks sensitive data 7.7 0.4% n8n Feb 4 HIGH CVE-2026-1777 sagemaker: security flaw enables exploitation 7.2 0.5% sagemaker Feb 2 MEDI CVE-2026-1778 sagemaker: security flaw enables exploitation 5.9 0.2% sagemaker Feb 2

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