AI Threat Alert
AI Security Threat Feed
Latest CVEs affecting AI/ML systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers. Vulnerabilities are tracked from NVD, GitHub Advisory, CISA KEV, MITRE ATLAS, and enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings to ISO 42001, EU AI Act, NIST AI RMF, and OWASP LLM Top 10. Updated continuously as new CVEs are published.
- CVSS severity
- EPSS exploit probability
- Exploitation confidence
- AI-component classification
- Compliance mappings
AI/ML CVEs Tracked
Critical
New This Week
In CISA KEV
Latest AI Security Threats
Showing 20 of 2346 results — no patch CVE-2026-68746 Livebook: auth fail-open grants full server access 8.8 0.4% — Aug 5 MEDI CVE-2026-66885 Livebook: CSRF binds victim session to attacker 6.5 0.2% — Aug 5 HIGH E CVE-2026-66881 Livebook: path traversal in notebooks writes any file 8.1 0.4% — Aug 5 HIGH CVE-2026-66298 Livebook: sandboxed JS bypasses origin check, forces exec 8.8 0.2% — Aug 5 MEDI E CVE-2026-18959 InnoShop: path traversal in file manager deletes files 5.4 0.4% — Aug 5 CRIT CVE-2026-9205 Langflow: weak Fernet key derivation exposes secrets 9.8 0.2% langflow Aug 5 HIGH CVE-2026-9201 Langflow: truncated-hash bypass enables RCE 8.8 0.2% langflow Aug 5 HIGH CVE-2026-9196 Langflow: RCE via unapproved LLM-generated code execution 8.8 0.3% langflow Aug 5 HIGH CVE-2026-9130 Langflow: authz bypass leaks cross-user chat history 7.1 0.2% langflow Aug 5 HIGH CVE-2026-8478 Langflow: RCE via arbitrary code injection (CWE-94) 8.8 0.4% langflow Aug 5 CRIT CVE-2026-8470 Langflow: weak PRNG lets attackers decrypt stored secrets 9.1 0.1% langflow Aug 5 HIGH CVE-2026-8183 Langflow: path traversal exposes arbitrary files 7.7 0.4% langflow Aug 5 HIGH CVE-2026-8182 Langflow: pre-auth RCE via chained HTTP requests 8.8 0.4% langflow Aug 5 MEDI CVE-2026-7869 Langflow: path traversal allows arbitrary file write 5.4 0.2% langflow Aug 5 MEDI CVE-2026-7658 Langflow: username path traversal enables data destruction 6.5 0.3% langflow Aug 5 CRIT E CVE-2026-48168 PraisonAI: shell injection in Claude Action enables RCE 10.0 0.9% praisonai Aug 5 HIGH CVE-2026-17633 Langflow: authenticated code injection enables RCE 8.8 0.4% langflow Aug 5 HIGH CVE-2026-17632 Langflow: AST code scanner bypass enables auth'd RCE 8.8 0.7% langflow Aug 5 HIGH CVE-2026-17624 Langflow: authenticated RCE via unsafe module imports 8.8 0.4% langflow Aug 5 HIGH CVE-2026-10547 Langflow: broken access control enables cache poisoning 8.1 0.2% langflow Aug 5 Frequently asked questions
What is an AI security threat feed?
An AI security threat feed is a continuously updated stream of vulnerabilities (CVEs) affecting AI and machine-learning systems — LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — filtered out of the broader CVE firehose and enriched for relevance.
Which sources are the AI CVEs tracked from?
CVEs are tracked from NVD, GitHub Advisory, CISA KEV, and MITRE ATLAS, then enriched with CVSS, EPSS, exploitation confidence, AI-component classification, and compliance mappings.
What AI systems do these vulnerabilities affect?
Coverage spans LLM frameworks, ML libraries, AI agents, vector databases, and inference servers — the components most security teams now run in production.
How often is the AI threat feed updated?
The feed updates continuously as new CVEs are published and enriched, so the most recent AI/ML vulnerabilities appear at the top.
Is the AI security feed free?
Yes — the public feed is free to browse. A Pro subscription adds breaking alerts, MITRE ATLAS mappings, compliance reports (ISO 42001, EU AI Act), and full CISO analysis.
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