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
MEDI E CVE-2026-90878 A vulnerability was determined in vllm-project... 4.3 0.3% — Sep 15 HIGH CVE-2026-91771 Weights & Biases wandb before 0.29.0 fails to... 8.8 0.7% — Sep 15 HIGH E CVE-2026-79411 Incorrect privilege assignment in the admin... 8.8 0.3% — Sep 15 UNKN CVE-2026-18117 Concrete CMS 9.0.0 through 9.5.3 is vulnerable to... — 0.3% — Sep 14 CRIT CVE-2026-12944 IBM Langflow OSS 1.0.0 through 1.10.0 can allow... 9.6 0.2% — Sep 14 MEDI E CVE-2026-90818 A security flaw has been discovered in... 4.3 0.5% — Sep 14 HIGH CVE-2026-81902 Concrete CMS 9 through 9.5.2 did not validate a... 8.1 0.2% — Sep 14 MEDI CVE-2026-7884 IBM Cognos Analytics 12.1.0 through 12.1.3 FP1,... 5.4 0.2% — Sep 14 MEDI CVE-2026-12767 IBM Langflow OSS 1.0.0 through 1.11.5 is... 6.5 0.2% — Sep 14 MEDI CVE-2026-12766 IBM Langflow OSS 1.0.0 through 1.11.2 is... 5.4 0.2% — Sep 14 MEDI CVE-2026-12765 IBM Langflow OSS 1.0.0 through 1.10.2 is... 6.5 0.2% — Sep 14 MEDI CVE-2026-12763 IBM Langflow OSS 1.0.0 through 1.11.5 could allow... 4.2 0.1% — Sep 14 MEDI E CVE-2026-55093 Tract is a tiny, no-nonsense, self-contained... 6.1 0.2% — Sep 14 MEDI CVE-2026-17628 IBM Langflow OSS 1.0.0 through 1.10.2 could allow... 5.4 0.3% — Sep 14 MEDI CVE-2026-73497 MCP Atlassian is a Model Context Protocol (MCP)... 6.5 0.2% mcp-atlassian Sep 14 HIGH E CVE-2026-73496 MCP Atlassian is a Model Context Protocol (MCP)... 7.7 0.3% mcp-atlassian Sep 14 HIGH CVE-2026-50270 dd-trace-java: baggage header parsing causes DoS 7.5 0.6% — Sep 14 HIGH CVE-2026-90943 Filament Comments: stored XSS via admin panel 8.7 0.2% — Sep 14 CRIT CVE-2026-57145 PraisonAI: path traversal lets agents read/write any file 9.1 0.4% praisonai Sep 14 HIGH E CVE-2026-57132 PraisonAI: auth bypass on agent invoke endpoint 8.2 0.3% praisonai Sep 14

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