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 1604 results
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2024-14021 llamaindex: Deserialization enables RCE 7.8 0.1% llamaindex Jan 12 HIGH E CVE-2026-22033 label-studio: XSS enables session hijacking — 0.0% label-studio Jan 12 HIGH CVE-2025-14279 mlflow: security flaw enables exploitation 8.1 0.0% mlflow Jan 12 HIGH E CVE-2026-22773 vllm: Resource Exhaustion enables DoS 7.5 0.0% vllm Jan 10 HIGH E CVE-2026-22612 fickling: Deserialization enables RCE — 0.1% fickling Jan 9 HIGH E CVE-2026-22609 fickling: Allowlist Bypass evades input filtering — 0.1% fickling Jan 9 HIGH E CVE-2026-22608 fickling: Allowlist Bypass evades input filtering — 0.0% fickling Jan 9 HIGH E CVE-2026-22607 fickling: Allowlist Bypass evades input filtering — 0.1% fickling Jan 9 HIGH E CVE-2026-22606 fickling: Allowlist Bypass evades input filtering — 0.1% fickling Jan 9 MEDI E CVE-2025-14980 BetterDocs: Info Disclosure leaks sensitive data 6.5 0.0% — 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 CVE-2026-21894 n8n: security flaw enables exploitation 6.5 0.0% n8n Jan 8 CRIT E CVE-2026-21877 n8n: Code Injection enables RCE 9.9 13.3% n8n Jan 8 CRIT CVE-2026-21858 n8n: Input Validation flaw enables exploitation 10.0 5.7% n8n Jan 8 HIGH E CVE-2025-66786 OAI CN5G AMF: unauthenticated JSON DoS on 5G SBI interface 7.5 0.2% oai-cn5g-amf Jan 7 HIGH E CVE-2025-65805 OAI CN5G AMF: Unauthenticated buffer overflow, RCE/DoS 7.5 0.2% oai-cn5g-amf Jan 7 MEDI E CVE-2026-21851 monai: Path Traversal enables file access 5.3 0.0% monai Jan 6 MEDI E CVE-2025-14371 AI component: Missing Auth allows unauthorized operations 4.3 0.0% — Jan 6 HIGH E CVE-2026-0621 mcp_typescript_sdk: security flaw enables exploitation 7.5 0.0% — Jan 5

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