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 766 results — Active exploitation, no patchCrewAI: RCE via Docker fallback in CodeInterpreter
CVE-2026-2275 OpenUI: hard-coded LiteLLM master key credential leak
CVE-2026-4993 @mobilenext/mobile-mcp: path traversal via AI agent tool
CVE-2026-33989 smolagents: code injection via incomplete sandbox fix
CVE-2026-4963 MLflow: broken access control exposes experiment traces
CVE-2025-15381 Wallos: SSRF allows internal network access
CVE-2026-33401 langflow: Access Control bypass enables privilege escalation
CVE-2026-33484 langflow: security flaw enables exploitation
CVE-2026-33475 AI component: IDOR enables unauthorized data access
CVE-2026-30886 AI component: Input Validation flaw enables exploitation
CVE-2026-4538 langflow: Code Injection enables RCE
CVE-2026-33017 nltk: Path Traversal enables file access
CVE-2026-33236 deepdiff: DoS causes service disruption
CVE-2026-33155 onnx: Integrity Verification bypass enables tampering
CVE-2026-28500 OpenClaw: RCE via request-side prompt injection
CVE-2026-30741 vllm: SSRF allows internal network access
CVE-2026-25960 Flowise: auth bypass exposes NVIDIA NIM container endpoints
CVE-2026-30824 Flowise: IDOR enables account takeover and SSO bypass
CVE-2026-30823 Flowise: mass assignment allows unauthenticated DB injection
CVE-2026-30822 flowise: Arbitrary File Upload enables RCE
CVE-2026-30821 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