AI Threat Alert AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

76

New This Week

16

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 1604 results
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2025-33213 NVIDIA: Deserialization enables RCE 8.8 0.1% — Dec 9 HIGH E CVE-2025-65964 n8n: security flaw enables exploitation 8.8 0.0% n8n Dec 9 MEDI E CVE-2025-13922 AI component: SQL Injection exposes database 6.5 0.0% — Dec 6 HIGH CVE-2025-34291 langflow: security flaw enables exploitation 8.8 10.9% langflow Dec 5 HIGH E CVE-2025-65958 open-webui: SSRF allows internal network access 8.5 0.1% open-webui Dec 4 UNKN CVE-2025-66479 Anthropic: Protection Bypass circumvents security controls — 0.0% — Dec 4 LOW E CVE-2025-63681 open-webui: Access Control bypass enables privilege escalation — 0.0% open-webui Dec 4 HIGH E CVE-2025-66404 mcp-server-kubernetes: Command Injection enables RCE 8.8 0.3% — Dec 3 MEDI CVE-2025-13359 taxopress: SQL Injection exposes database 6.5 0.0% — Dec 3 MEDI CVE-2025-13354 taxopress: Missing Auth allows unauthorized operations 4.3 0.0% — Dec 3 HIGH CVE-2025-66448 vllm: Code Injection enables RCE 8.8 0.0% vllm Dec 1 UNKN E CVE-2025-12638 Keras: Path Traversal enables file access — 0.0% — Nov 28 CRIT CVE-2025-34351 ray: security flaw enables exploitation — 0.5% ray Nov 27 CRIT CVE-2025-62593 ray: Code Injection enables RCE — 0.0% ray Nov 26 HIGH CVE-2025-65106 langchain-core: security flaw enables exploitation — 0.1% langchain-core Nov 21 HIGH E CVE-2025-62609 mlx: security flaw enables exploitation 7.5 0.1% mlx Nov 21 CRIT E CVE-2025-62608 mlx: security flaw enables exploitation 9.1 0.1% mlx Nov 21 HIGH E CVE-2025-12973 AI component: Arbitrary File Upload enables RCE 7.2 0.1% — Nov 21 MEDI CVE-2025-62426 vllm: Resource Exhaustion enables DoS 6.5 0.1% vllm Nov 21 MEDI CVE-2025-62372 vllm: security flaw enables exploitation 6.5 0.1% vllm Nov 21

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