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 4330 resultsCVE-2026-54352Budibase: zip symlink bypass exposes all server secrets9.60.5%@budibase/serverJun 22HIGHECVE-2026-54232vLLM: dependency confusion RCE backdoors container images8.80.6%vllmJun 22HIGHECVE-2026-50132Budibase: account hijack via chat identity CSRF7.30.2%—Jun 22HIGHECVE-2025-71358picklescan: scanner bypass enables RCE via pickle8.10.3%picklescanJun 22HIGHECVE-2025-71344picklescan: scanner bypass enables undetected pickle RCE8.10.5%picklescanJun 22HIGHECVE-2025-71339picklescan: scanner bypass enables arbitrary code execution8.10.4%picklescanJun 22HIGHCVE-2026-55409Filament: stored XSS in disabled RichEditor field7.60.4%—Jun 22MEDICVE-2026-48067Filament: auth bypass via Livewire state tampering6.50.3%—Jun 22MEDICVE-2026-48167Filament: stored XSS in ImageColumn/ImageEntry6.40.2%—Jun 22MEDICVE-2026-48500Filament: unauth file upload drains disk/inflates costs6.50.3%filament/filamentJun 22MEDICVE-2026-48166Filament: timing side-channel exposes registered emails5.30.3%—Jun 22HIGHCVE-2026-48505Filament: MFA race condition enables recovery code reuse7.40.3%—Jun 22MEDICVE-2026-56357n8n: webhook forgery enables unauthorized workflow execution4.00.3%n8nJun 22CRITCVE-2026-56348n8n: SSRF bypasses allowlist, exfiltrates credentials9.10.5%n8nJun 22HIGHECVE-2026-56268Flowise: cross-workspace chatflow config disclosure7.70.4%FlowiseJun 22MEDICVE-2026-55443LangChain: path traversal exposes files outside agent root5.50.2%langchainJun 22MEDIECVE-2026-12479Keras: path traversal via layer names allows arbitrary file write6.10.4%kerasJun 22HIGHCVE-2026-10845WebSphere AS: JAX-WS auth bypass, unauthorized access7.30.5%—Jun 22HIGHECVE-2026-56104Chainlit: session hijacking via WebSocket restoration8.20.4%chainlitJun 22CRITCVE-2026-10561Langflow: auth bypass + unauthenticated RCE (CVSS 10)10.00.8%langflowJun 22Frequently 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