AI Threat Alert
AI 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 3021 results CVE-2026-53822 OpenClaw: TOCTOU command injection bypasses allowlist 8.8 1.0% OpenClaw Jun 12 HIGH CVE-2026-53821 OpenClaw: auth bypass grants admin RPC via WebSocket 8.8 0.3% OpenClaw Jun 12 MEDI CVE-2026-53820 OpenClaw: exec denylist bypass via MCP session-spawn 6.6 0.1% OpenClaw Jun 12 MEDI CVE-2026-47345 typo3/html-sanitizer: XSS bypass via namespace encoding — 0.4% typo3/html-sanitizer Jun 12 MEDI E CVE-2026-48148 Budibase: SSRF via VectorDB host exposes cloud metadata — 0.2% @budibase/server Jun 12 UNKN CVE-2026-8828 ChromaDB: tenant isolation bypass exposes all tenant data — 0.3% chromadb Jun 12 HIGH E CVE-2026-45833 ChromaDB: RCE via trust_remote_code in collection update 8.8 0.3% chromadb Jun 12 HIGH CVE-2026-45832 ChromaDB: V1 auth bypass exposes all tenant collections 8.8 0.3% chromadb Jun 12 HIGH CVE-2026-45831 ChromaDB: RBAC bypass enables cross-tenant data access 8.8 0.2% chromadb Jun 12 HIGH CVE-2026-45830 ChromaDB: auth bypass exposes any tenant's collections 8.8 0.3% chromadb Jun 12 HIGH E CVE-2026-48146 Budibase: SSRF in OAuth2 exposes cloud credentials 7.7 0.2% @budibase/server Jun 12 MEDI CVE-2026-48121 LangGraph MongoDB: NoSQL injection leaks tenant checkpoints 6.7 0.2% @langchain/langgraph-checkpoint-mongodb Jun 12 UNKN E CVE-2026-49347 QuestBot: resource exhaustion via unlimited ticket creation — 0.2% — Jun 12 MEDI CVE-2026-50634 Apache CXF: JWS signature bypass exposes JAX-RS APIs 6.5 0.3% — Jun 12 HIGH CVE-2026-53819 OpenClaw: RCE via workspace .env executable override 8.8 0.3% openclaw Jun 11 MEDI CVE-2026-53818 OpenClaw: MCP loopback auth bypass enables policy evasion 6.6 0.1% openclaw Jun 11 HIGH CVE-2026-53817 OpenClaw: locality spoof yields durable admin credentials 8.8 0.3% openclaw Jun 11 HIGH CVE-2026-53816 OpenClaw: node event forgery bypasses exec authorization 7.2 0.3% openclaw Jun 11 MEDI CVE-2026-53815 OpenClaw: auth bypass exposes restricted channel messages 6.5 0.2% openclaw Jun 11 HIGH CVE-2026-53814 OpenClaw: privilege escalation via hook-triggered MCP scope 8.3 0.3% openclaw Jun 11 Frequently 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