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 435 results — High severity, Active exploitationfickling: Allowlist Bypass evades input filtering
CVE-2026-22606 OAI CN5G AMF: unauthenticated JSON DoS on 5G SBI interface
CVE-2025-66786 OAI CN5G AMF: Unauthenticated buffer overflow, RCE/DoS
CVE-2025-65805 mcp_typescript_sdk: security flaw enables exploitation
CVE-2026-0621 lmdeploy: Deserialization enables RCE
CVE-2025-67729 langchain-core: Deserialization enables RCE
CVE-2025-68664 n8n: security flaw enables exploitation
CVE-2025-68613 langflow: File Control enables path manipulation
CVE-2025-68478 nbconvert: security flaw enables exploitation
CVE-2025-53000 fickling: Code Injection enables RCE
CVE-2025-67748 fickling: Allowlist Bypass evades input filtering
CVE-2025-67747 n8n: security flaw enables exploitation
CVE-2025-65964 langflow: security flaw enables exploitation
CVE-2025-34291 open-webui: SSRF allows internal network access
CVE-2025-65958 mcp-server-kubernetes: Command Injection enables RCE
CVE-2025-66404 mlx: security flaw enables exploitation
CVE-2025-62609 AI component: Arbitrary File Upload enables RCE
CVE-2025-12973 open-webui: Code Injection enables RCE
CVE-2025-64496 Open WebUI: XSS-to-RCE via malicious prompt injection
CVE-2025-64495 langgraph-checkpoint: Deserialization enables RCE
CVE-2025-64439 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