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

75

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 1092 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
CRIT CVE-2026-25053 n8n: Command Injection enables RCE 9.9 0.0% n8n Feb 4 CRIT CVE-2026-25052 n8n: security flaw enables exploitation 9.9 0.0% n8n Feb 4 MEDI CVE-2026-25051 n8n: XSS enables session hijacking 5.4 0.0% n8n Feb 4 CRIT CVE-2026-25049 n8n: security flaw enables exploitation 9.9 0.0% n8n Feb 4 HIGH CVE-2025-61917 n8n: Info Disclosure leaks sensitive data 7.7 0.0% n8n Feb 4 CRIT CVE-2026-22778 vllm: security flaw enables exploitation 9.8 0.1% vllm Feb 2 CRIT E CVE-2026-25481 langroid: Code Injection enables RCE — 0.0% — Feb 2 HIGH E CVE-2026-0599 text-generation: DoS causes service disruption 7.5 0.3% — Feb 2 CRIT E CVE-2026-25130 cai-framework: Command Injection enables RCE 9.7 0.0% — Jan 30 LOW CVE-2026-25211 llama-stack: security flaw enables exploitation 3.2 0.0% — Jan 30 HIGH E CVE-2026-24780 agpt: Code Injection enables RCE 8.8 0.1% — Jan 29 MEDI GHSA-gpx9-96j6-pp87 agentos-taskweaver: Protection Bypass circumvents security controls 6.5 — — Jan 28 HIGH E CVE-2026-24779 vllm: SSRF allows internal network access 7.1 0.0% vllm Jan 27 HIGH E CVE-2026-24747 pytorch: Code Injection enables RCE 8.8 0.1% pytorch Jan 27 CRIT E CVE-2026-1470 n8n: Code Injection enables RCE 9.9 1.9% n8n Jan 27 MEDI E CVE-2026-24123 bentoml: Path Traversal enables file access 6.5 0.0% bentoml Jan 26 CRIT E CVE-2025-13374 Kalrav: Arbitrary File Upload enables RCE 9.8 0.1% — Jan 24 UNKN CVE-2026-0772 langflow: Deserialization enables RCE — 0.9% langflow Jan 23 UNKN CVE-2026-0771 langflow: Code Injection enables RCE — 0.1% langflow Jan 23 HIGH CVE-2026-0770 langflow: security flaw enables exploitation — 11.9% langflow Jan 23

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