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 533 results — Critical severityCVE-2026-46858Oracle APM: unauthenticated write/DoS via JVM Diagnostics9.10.4%APM - Application Performance ManagementJun 16CRITECVE-2026-48746vllm: auth bypass exposes OpenAI inference API9.11.2%vllmJun 16CRITECVE-2026-48519Langflow: unauthenticated RCE via Shareable Playground9.60.8%langflowJun 16CRITCVE-2026-53838OpenClaw: approval scope bypass via reconnection state9.80.2%OpenClawJun 12CRITECVE-2026-46703Boxlite: OCI symlink traversal enables host RCE9.60.5%boxliteJun 10CRITECVE-2026-46442Flowise: sandbox escape enables authenticated RCE9.933.0%flowiseJun 8CRITECVE-2026-46441Flowise: mass assignment breaks multi-tenant isolation9.60.3%flowiseJun 8CRITECVE-2026-46440Flowise: plaintext auth brute-force, no rate limit9.10.2%flowiseJun 8CRITGHSA-8whc-2wmv-ww35AVideo YPTSocket: Stored DOM XSS enables admin takeover9.6—WWBN/AVideoJun 4CRITECVE-2026-44180Jupyter Enterprise Gateway: root privilege bypass in Kubernetes9.80.7%jupyter_enterprise_gatewayJun 3CRITECVE-2026-5241transformers: trust_remote_code bypass enables RCE via model load9.60.6%transformersJun 3CRITCVE-2026-47117OpenMed: RCE via trust_remote_code model loading9.80.9%openmedJun 2CRITCVE-2026-9319IBM WebSphere: RCE via JAX-WS deserialization (CVSS 9.0)9.00.5%—Jun 1CRITECVE-2026-47413praisonai-platform: member can escalate to workspace owner9.60.3%praisonai-platformJun 1CRITECVE-2026-47416praisonai-platform: member-to-owner privilege escalation9.60.3%praisonai-platformMay 29CRITECVE-2026-47410praisonai-platform: hardcoded JWT → full account takeover9.80.4%praisonai-platformMay 29CRITECVE-2026-47407praisonai-platform: IDOR enables cross-tenant agent hijack—0.3%praisonai-platformMay 29CRITECVE-2026-47391PraisonAI: Unauth RCE via A2A eval injection9.81.5%PraisonAIMay 29CRITECVE-2026-47392praisonaiagents: RCE via Python sandbox bypass9.90.9%PraisonAIMay 29CRITECVE-2026-47393PraisonAI: auth bypass in deployed API exposes LLM + tools9.80.6%PraisonAIMay 29Frequently 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