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 1092 results — no patchtransformers: Deserialization enables RCE
CVE-2025-14920 local-deep-research: SSRF allows internal network access
CVE-2025-67743 n8n: security flaw enables exploitation
CVE-2025-68613 langflow: File Control enables path manipulation
CVE-2025-68478 langflow: SSRF allows internal network access
CVE-2025-68477 nbconvert: security flaw enables exploitation
CVE-2025-53000 anythingllm: Missing Auth allows unauthenticated access
CVE-2025-63390 ollama: Missing Auth allows unauthenticated access
CVE-2025-63389 cai-framework: Command Injection enables RCE
CVE-2025-67511 NVIDIA: Deserialization enables RCE
CVE-2025-33213 n8n: security flaw enables exploitation
CVE-2025-65964 AI component: SQL Injection exposes database
CVE-2025-13922 langflow: security flaw enables exploitation
CVE-2025-34291 Anthropic: Protection Bypass circumvents security controls
CVE-2025-66479 open-webui: Access Control bypass enables privilege escalation
CVE-2025-63681 mcp-server-kubernetes: Command Injection enables RCE
CVE-2025-66404 taxopress: SQL Injection exposes database
CVE-2025-13359 taxopress: Missing Auth allows unauthorized operations
CVE-2025-13354 vllm: Code Injection enables RCE
CVE-2025-66448 Keras: Path Traversal enables file access
CVE-2025-12638 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