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-2026-67620Flowise: SSRF bypass exposes cloud metadata credentials7.70.5%flowiseAug 8HIGHCVE-2026-64636Plesk Obsidian: authenticated SQLi exposes panel DB7.70.4%—Aug 7HIGHECVE-2026-70636Flowise: auth bypass triggers unauthorized OAuth refresh7.50.7%FlowiseAug 6HIGHECVE-2026-67621Flowise: broken authz lets viewers poison RAG stores7.60.4%FlowiseAug 6HIGHCVE-2026-54763Traefik: underscore header bypass spoofs identity—0.2%github.com/traefik/traefik/v3Aug 6HIGHCVE-2026-43632llama.cpp: UAF race in tokenize endpoints risks RCE8.10.5%—Aug 6HIGHCVE-2026-57819Apache CXF: JAX-RS form parameter flood enables DoS7.50.7%—Aug 6HIGHECVE-2026-69111Milvus: unauthenticated DoS via /management/stop7.51.1%milvusAug 5HIGHCVE-2026-68746Livebook: auth fail-open grants full server access8.80.8%—Aug 5HIGHECVE-2026-66881Livebook: path traversal in notebooks writes any file8.10.6%—Aug 5HIGHCVE-2026-66298Livebook: sandboxed JS bypasses origin check, forces exec8.80.3%—Aug 5HIGHECVE-2026-55524PraisonAI: SSRF bypass in web_crawl via TOCTOU/rebinding7.50.2%praisonaiagentsAug 5HIGHECVE-2026-55523PraisonAI: SSRF via redirect bypass in web_crawl()—0.5%praisonaiagentsAug 5HIGHECVE-2026-55522PraisonAI: RCE via workflow include bypasses safe loader7.80.2%PraisonAIAug 5HIGHCVE-2026-9201Langflow: truncated-hash bypass enables RCE8.80.4%langflowAug 5HIGHCVE-2026-9196Langflow: RCE via unapproved LLM-generated code execution8.80.5%langflowAug 5HIGHCVE-2026-9130Langflow: authz bypass leaks cross-user chat history7.10.3%langflowAug 5HIGHCVE-2026-8478Langflow: RCE via arbitrary code injection (CWE-94)8.80.6%langflowAug 5HIGHCVE-2026-8183Langflow: path traversal exposes arbitrary files7.70.6%langflowAug 5HIGHCVE-2026-8182Langflow: pre-auth RCE via chained HTTP requests8.80.7%langflowAug 5Frequently 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