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.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 337 results — Critical severity GHSA-vvpj-8cmc-gx39 picklescan: security flaw enables exploitation 10.0 — picklescan Mar 3 CRIT GHSA-7wx9-6375-f5wh picklescan: Allowlist Bypass evades input filtering 9.8 — picklescan Mar 3 CRIT E CVE-2026-27966 langflow: Code Injection enables RCE 9.8 33.7% langflow Feb 26 CRIT E CVE-2026-27577 n8n: Code Injection enables RCE 9.9 10.2% n8n Feb 25 CRIT CVE-2026-27495 n8n: Code Injection enables RCE 9.9 0.6% n8n Feb 25 CRIT CVE-2026-27494 n8n: security flaw enables exploitation 9.9 0.4% n8n Feb 25 CRIT CVE-2026-27493 n8n: Code Injection enables RCE 9.0 1.1% n8n Feb 25 CRIT CVE-2026-2635 mlflow: security flaw enables exploitation 9.8 1.1% mlflow Feb 20 CRIT CVE-2026-26030 semantic-kernel: Code Injection enables RCE 10.0 2.9% semantic-kernel Feb 19 CRIT E CVE-2026-2654 smolagents: SSRF allows internal network access 9.8 0.4% smolagents Feb 18 CRIT CVE-2025-14014 Smart Panel: unauthenticated file upload enables RCE 9.8 0.4% Smart Panel Feb 12 CRIT CVE-2026-25592 semantic-kernel: Path Traversal enables file access 9.9 1.9% semantic-kernel Feb 6 CRIT CVE-2026-25115 n8n: Protection Bypass circumvents security controls 9.9 0.5% 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 CRIT CVE-2026-25049 n8n: security flaw enables exploitation 9.9 1.2% n8n Feb 4 CRIT CVE-2026-22778 vllm: security flaw enables exploitation 9.8 3.3% vllm Feb 2 CRIT E CVE-2026-25481 langroid: Code Injection enables RCE — 0.6% langroid Feb 2 CRIT E CVE-2026-25130 cai-framework: Command Injection enables RCE 9.7 0.8% — Jan 30 CRIT E CVE-2026-1470 n8n: Code Injection enables RCE 9.9 18.7% n8n Jan 27 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