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-2026-45399Open WebUI: task auth bypass enables cross-user DoS7.10.3%open-webuiMay 14HIGHECVE-2026-45398open-webui: IDOR exposes private RAG knowledge bases7.50.3%open-webuiMay 14HIGHECVE-2026-45350open-webui: missing authz allows admin tool hijacking7.10.3%open-webuiMay 14HIGHECVE-2026-45349open-webui: auth bypass exposes all user chat histories7.10.2%open-webuiMay 14HIGHECVE-2026-45338open-webui: SSRF via OAuth picture claim leaks internal data7.70.4%open-webuiMay 14HIGHECVE-2026-45331open-webui: SSRF bypass exposes cloud IAM credentials8.50.3%open-webuiMay 14HIGHECVE-2026-45314Open WebUI: Stored XSS via webhook SVG profile image—0.2%open-webuiMay 14HIGHECVE-2026-45315open-webui: stored XSS → JWT theft and admin takeover8.70.2%open-webuiMay 14HIGHCVE-2026-8597SageMaker: RCE via poisoned Triton model artifacts in S37.20.5%sagemakerMay 14HIGHECVE-2026-45303Open WebUI: XSS iframe allows auth token exfiltration7.70.2%open-webuiMay 14HIGHECVE-2026-45301open-webui: BOLA exposes all users' uploaded files8.10.3%open-webuiMay 14HIGHECVE-2026-8629Crabbox: IDOR lets viewers hijack Code/VNC/Egress8.10.3%crabboxMay 14HIGHCVE-2026-8621Crabbox: header spoofing bypasses lease auth8.80.4%crabboxMay 14HIGHGHSA-wxrr-jp8m-qq7fFlowise: mass assignment enables cross-workspace IDOR——flowiseMay 14HIGHGHSA-mq53-pc65-wjc4Flowise: mass assignment breaks workspace isolation——flowiseMay 14HIGHGHSA-7j65-65cr-6644Flowise: mass assignment breaks cross-workspace isolation——flowiseMay 14HIGHGHSA-5h9v-837x-m97rFlowise: mass assignment enables cross-workspace data takeover——flowiseMay 14HIGHGHSA-728h-4mwj-f2p4Flowise: mass assignment breaks cross-workspace isolation——flowiseMay 14HIGHGHSA-78pr-c5x5-jggcFlowise: IDOR via mass assignment breaks tenant isolation——flowiseMay 14HIGHGHSA-hmg2-jjjx-jcp2Flowise: missing authz on vector store CRUD endpoints——flowiseMay 14Frequently 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