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 4307 resultsCVE-2026-87995Open WebUI: XSS in terminal preview hijacks user accounts8.70.4%open-webuiSep 9MEDIECVE-2026-87994Open WebUI: channel authz gap allows message spoofing4.30.4%open-webuiSep 9MEDICVE-2026-87017Open WebUI: KB metadata leaks across tenants in 11 backends4.30.4%open-webuiSep 9HIGHECVE-2026-87016Open WebUI: OAuth wildcard bug hijacks admin sessions8.10.6%open-webuiSep 9MEDIECVE-2026-87015Open WebUI: session cookies leak to rogue tool server6.80.5%open-webuiSep 9MEDIECVE-2026-87014Open WebUI: demoted admins keep socket access to all notes6.50.5%open-webuiSep 9MEDIECVE-2026-87013Open WebUI: authenticated DoS via folder cycle4.30.5%open-webuiSep 9MEDIECVE-2026-87012Open WebUI: type confusion suppresses all reminders4.30.5%open-webuiSep 9HIGHECVE-2026-87011Open WebUI: unauth DoS via OIDC logout handler7.50.6%open-webuiSep 9HIGHCVE-2026-86099Chainlit: path traversal via sessionId wipes directories8.20.6%chainlitSep 9MEDIECVE-2026-87820CyberPanel: AI Scanner endpoints leak admin usernames unauthenticated5.30.9%—Sep 9HIGHECVE-2026-87811SiYuan: stored XSS in notebook template paths7.30.4%—Sep 9HIGHCVE-2026-83593WPBot: unauth stored XSS in chatbot conversation field7.20.5%WPBot – AI ChatBot for Live Support, Lead Generation, AI ServicesSep 9HIGHCVE-2026-12855InsydeH2O: BIOS memory corruption enables local RCE8.20.2%InsydeH2OSep 9HIGHCVE-2026-6485InsydeH2O UEFI: BIOS Shell allows Secure Boot bypass8.20.2%InsydeH2OSep 9MEDICVE-2026-86995n8n Git node: config injection leaks local files—0.4%n8nSep 8MEDICVE-2026-86994n8n: broken authZ leaks workflow IDs to any member—0.3%n8nSep 8MEDICVE-2026-86993n8n: cross-project credential theft via Log Streaming—0.5%n8nSep 8MEDICVE-2026-86085n8n: missing scope check leaks project member emails—0.4%n8nSep 8MEDICVE-2026-86084n8n: stale OIDC endpoint bypasses disabled SSO—0.5%n8nSep 8Frequently 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