AI Threat AlertAI 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 1908 results — High severityCVE-2026-17633Langflow: authenticated code injection enables RCE8.80.7%langflowAug 5HIGHCVE-2026-17632Langflow: AST code scanner bypass enables auth'd RCE8.80.9%langflowAug 5HIGHCVE-2026-17624Langflow: authenticated RCE via unsafe module imports8.80.7%langflowAug 5HIGHCVE-2026-10547Langflow: broken access control enables cache poisoning8.10.4%langflowAug 5HIGHCVE-2026-9081Langflow: SSRF in Ollama config hits internal hosts7.10.3%Langflow OSSAug 5HIGHCVE-2026-17625Langflow: RCE via authenticated OS command injection7.20.8%Langflow OSSAug 5HIGHCVE-2026-9077Langflow: MCP config write bypasses localhost restriction8.50.4%langflowAug 5HIGHCVE-2026-8446Langflow: OAuth auth bypass on MCP composer endpoint7.50.5%langflowAug 5HIGHCVE-2026-17630Langflow: RCE via improper config parameter validation8.80.8%langflowAug 5HIGHCVE-2026-17626Langflow: Docker MCP volume-mount flaw exposes host files8.80.4%langflowAug 5HIGHCVE-2026-17623Langflow: MCP config command injection allows RCE8.80.8%langflowAug 5HIGHECVE-2026-67623Mistral Vibe: RCE via malicious git fsmonitor hook8.81.1%mistral-vibeAug 5HIGHCVE-2026-71281peft: unsafe torch.load in LoRA-GA/CorDA allows RCE8.80.5%peftAug 5HIGHCVE-2026-71211MLflow AI Gateway: SSRF via unvalidated api_base7.10.3%mlflowAug 5HIGHECVE-2026-6639AIWU WP Plugin: unauth leak of stored OpenAI keys7.52.0%—Aug 5HIGHCVE-2026-70494Open WebUI: broken authz lets collaborator delete chats8.10.5%open-webuiAug 4HIGHECVE-2026-70492Open WebUI: KaTeX fallback XSS steals admin session8.70.4%open-webuiAug 4HIGHECVE-2026-70486Open WebUI: iframe sandbox bypass = account takeover8.20.4%open-webuiAug 4HIGHECVE-2026-70485Open WebUI: NAT64 IPv6 trick bypasses SSRF filter, leaks metadata7.10.4%open-webuiAug 4HIGHECVE-2026-70482Open WebUI: OAuth token exchange enables takeover8.10.6%open-webuiAug 4Frequently 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