AI Security Threat Feed
Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 160 results — Critical severity, Active exploitationMLflow: path traversal enables sandbox escape, file overwrite
CVE-2025-15036 langflow: security flaw enables exploitation
CVE-2026-33475 langflow: Path Traversal enables file access
CVE-2026-33309 langflow: Code Injection enables RCE
CVE-2026-33017 mlflow: Path Traversal enables file access
CVE-2025-15031 onnx: Integrity Verification bypass enables tampering
CVE-2026-28500 OpenClaw: RCE via request-side prompt injection
CVE-2026-30741 mcp-atlassian: Path Traversal enables file access
CVE-2026-27825 vllm: SSRF allows internal network access
CVE-2026-25960 Flowise: auth bypass exposes NVIDIA NIM container endpoints
CVE-2026-30824 flowise: Arbitrary File Upload enables RCE
CVE-2026-30821 langflow: Code Injection enables RCE
CVE-2026-27966 smolagents: SSRF allows internal network access
CVE-2026-2654 langroid: Code Injection enables RCE
CVE-2026-25481 cai-framework: Command Injection enables RCE
CVE-2026-25130 n8n: Code Injection enables RCE
CVE-2026-1470 Kalrav: Arbitrary File Upload enables RCE
CVE-2025-13374 n8n: Code Injection enables RCE
CVE-2026-0863 n8n: Input Validation flaw enables exploitation
CVE-2026-21858 langflow: Missing Auth allows unauthenticated access
CVE-2026-21445 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
AI Threat Alert