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 patchn8n: Input Validation flaw enables exploitation
CVE-2026-21858 OAI CN5G AMF: unauthenticated JSON DoS on 5G SBI interface
CVE-2025-66786 OAI CN5G AMF: Unauthenticated buffer overflow, RCE/DoS
CVE-2025-65805 AI component: Missing Auth allows unauthorized operations
CVE-2025-14371 mcp_typescript_sdk: security flaw enables exploitation
CVE-2026-0621 langflow: Missing Auth allows unauthenticated access
CVE-2026-21445 n8n: security flaw enables exploitation
CVE-2025-68697 n8n: Protection Bypass circumvents security controls
CVE-2025-68668 n8n: XSS enables session hijacking
CVE-2025-61914 lmdeploy: Deserialization enables RCE
CVE-2025-67729 langchain.js: Deserialization enables RCE
CVE-2025-68665 langchain-core: Deserialization enables RCE
CVE-2025-68664 Hugging Face smolagents: Unsafe deserialization in Remote Python Executor leads to RCE
CVE-2025-14931 transformers: Deserialization enables RCE
CVE-2025-14930 transformers: Deserialization enables RCE
CVE-2025-14929 transformers: Code Injection enables RCE
CVE-2025-14928 transformers: Code Injection enables RCE
CVE-2025-14927 transformers: Code Injection enables RCE
CVE-2025-14926 transformers: Deserialization enables RCE
CVE-2025-14924 transformers: Deserialization enables RCE
CVE-2025-14921 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