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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 2345 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2026-36467 Unrestricted Upload of File with Dangerous Type... 7.2 — — Sep 21 MEDI CVE-2026-94387 Aureus ERP before 1.6.0 contains a stored... 5.4 — — Sep 21 MEDI CVE-2026-94094 A flaw has been found in OpenClaw up to 2026.9.5.... 4.3 0.3% — Sep 20 LOW CVE-2026-93989 vLLM through 0.29.0 fails to properly validate... 3.1 0.2% — Sep 19 HIGH CVE-2026-93993 Mistral Vibe before 2.25.5 contains a remote code... 8.8 0.6% mistral-vibe Sep 19 HIGH CVE-2026-93923 SiYuan through 3.8.4 fails to escape heading... 8.8 0.4% — Sep 18 HIGH CVE-2026-93922 SiYuan through 3.8.4 renders notebook names as... 8.8 0.5% — Sep 18 LOW E CVE-2026-57225 Suricata is a network Intrusion Detection System,... 3.3 0.1% — Sep 18 LOW CVE-2026-93841 vLLM through 0.29.0 contains a memory corruption... 3.7 0.2% — Sep 18 LOW CVE-2026-93840 vLLM before 0.29.0 validates allowed_token_ids... 3.7 0.2% — Sep 18 HIGH E CVE-2026-93592 vLLM versions before 0.28.0 fail to validate the... 7.5 0.4% — Sep 18 HIGH E CVE-2026-93591 SiYuan versions before 3.8.3 contain an SQL... 7.6 0.3% — Sep 18 MEDI CVE-2026-89278 The GPTranslate – Multilingual AI Translation... 5.3 0.3% — Sep 18 HIGH CVE-2026-93436 vLLM through 0.29.0 fails to properly clean up... 7.5 0.5% — Sep 17 MEDI CVE-2026-14311 The Booking for Appointments and Events Calendar... 5.4 0.2% — Sep 17 HIGH CVE-2026-54507 Vvveb is a powerful and easy to use CMS with page... — 0.3% — Sep 17 HIGH CVE-2026-76154 A stored cross-site scripting vulnerability in... 7.3 0.4% — Sep 17 MEDI CVE-2026-93013 RAGFlow through 0.27.2 contains a path traversal... 4.3 0.3% — Sep 17 HIGH CVE-2026-92986 SiYuan before 3.8.4 renders document titles as... 8.8 0.4% — Sep 17 HIGH E CVE-2026-92985 SiYuan versions before 3.8.4 fail to escape... 8.8 0.5% — Sep 17

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