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 570 results — Medium severityn8n: XSS enables session hijacking
CVE-2025-61914 local-deep-research: SSRF allows internal network access
CVE-2025-67743 langflow: SSRF allows internal network access
CVE-2025-68477 anythingllm: Missing Auth allows unauthenticated access
CVE-2025-63390 AI component: SQL Injection exposes database
CVE-2025-13922 taxopress: SQL Injection exposes database
CVE-2025-13359 taxopress: Missing Auth allows unauthorized operations
CVE-2025-13354 vllm: Resource Exhaustion enables DoS
CVE-2025-62426 vllm: security flaw enables exploitation
CVE-2025-62372 AI component: Info Disclosure leaks sensitive data
CVE-2025-12732 AI component: SQL Injection exposes database
CVE-2025-11972 Better: security flaw enables exploitation
CVE-2025-12360 dspy: security flaw enables exploitation
CVE-2025-12695 Keras: safe_mode bypass enables file read and SSRF
CVE-2025-12058 smolagents: security flaw enables exploitation
CVE-2025-11844 Moodle: IDOR enables unauthorized data access
CVE-2025-60511 vllm: DoS via Jinja template injection in chat API
CVE-2025-61620 clearml: path traversal in safe_extract → RCE risk
CVE-2025-8917 TensorFlow: non-deterministic compilation breaks Embedding
CVE-2025-55556 PyTorch: integer overflow in nan_to_num causes DoS
CVE-2025-55554 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