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

2,390

AI/ML CVEs Tracked

342

Critical

360

New This Week

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 826 results — has patch

Severity CVE ID Summary CVSS EPSS Package Date

MEDI E CVE-2025-6208 llama-index-core: DoS causes service disruption 5.3 0.4% llama-index-core Feb 2 HIGH E CVE-2026-1117 lollms: Access Control bypass enables privilege escalation 8.2 0.4% lollms Feb 2 HIGH E CVE-2026-0599 text-generation: DoS causes service disruption 7.5 23.7% text-generation Feb 2 HIGH E CVE-2025-10279 mlflow: security flaw enables exploitation 7.0 0.2% mlflow Feb 2 LOW CVE-2026-25211 llama-stack: security flaw enables exploitation 3.2 0.2% llama-stack Jan 30 HIGH E CVE-2026-22219 chainlit: SSRF allows internal network access 7.7 4.4% chainlit Jan 20 HIGH CVE-2026-0897 keras: Resource Exhaustion enables DoS — 0.4% keras Jan 15 MEDI CVE-2025-68492 chainlit: IDOR enables unauthorized data access 4.2 0.2% chainlit Jan 14 HIGH CVE-2025-14279 mlflow: security flaw enables exploitation 8.1 0.2% mlflow Jan 12 HIGH E CVE-2026-22612 fickling: Deserialization enables RCE — 0.3% fickling Jan 9 HIGH E CVE-2026-22609 fickling: Allowlist Bypass evades input filtering — 0.6% fickling Jan 9 HIGH E CVE-2026-22608 fickling: Allowlist Bypass evades input filtering — 0.3% fickling Jan 9 HIGH E CVE-2026-22607 fickling: Allowlist Bypass evades input filtering — 0.4% fickling Jan 9 HIGH E CVE-2026-22606 fickling: Allowlist Bypass evades input filtering — 0.4% fickling Jan 9 HIGH GHSA-mcmc-2m55-j8jj vllm: Input Validation flaw enables exploitation 8.8 — vllm Jan 8 HIGH GHSA-9726-w42j-3qjr picklescan: Path Traversal enables file access — — picklescan Jan 8 MEDI E CVE-2026-21851 monai: Path Traversal enables file access 5.3 0.3% monai Jan 6 HIGH GHSA-46h3-79wf-xr6c picklescan: Code Injection enables RCE — — picklescan Dec 30 HIGH GHSA-955r-x9j8-7rhh picklescan: Code Injection enables RCE — — picklescan Dec 30 MEDI GHSA-6556-fwc2-fg2p picklescan: Code Injection enables RCE — — picklescan Dec 30

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