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 1961 results — Active exploitationCVE-2026-69147vLLM: request-selected video backend exhausts GPU memory6.50.6%vllmSep 16CRITECVE-2025-59953LMDeploy: unsafe pickle deserialization allows RCE9.80.9%lmdeploySep 16MEDIECVE-2026-87959WPBot: missing capability check exposes Claude API key5.40.2%wpbotSep 16HIGHECVE-2026-91938Flowise: SSRF in web loaders exposes cloud metadata7.10.4%flowiseSep 15HIGHECVE-2026-91937Flowise: NoSQL injection exposes other users' chat history7.50.5%flowiseSep 15MEDIECVE-2026-91936Flowise: CI script injection leaks AWS and Docker creds6.80.5%flowiseSep 15HIGHECVE-2026-91935Flowise: SSRF in chat-model baseURL leaks API keys8.30.4%flowiseSep 15HIGHECVE-2026-91933Flowise: cross-workspace tool access via realtime auth gap7.10.4%flowiseSep 15HIGHECVE-2026-91932Flowise: MCP cwd validation bypass enables RCE8.50.7%flowiseSep 15HIGHECVE-2026-91931Flowise: RCE via npx in Custom MCP node8.50.7%flowiseSep 15HIGHECVE-2026-91930Flowise: cross-tenant org admin takeover via IDOR7.50.4%flowiseSep 15LOWECVE-2026-91836OpenClaw ClawScan: incomplete comparison in static scanner2.80.3%openclawSep 15LOWECVE-2026-91835OpenClaw ClawScan: file classifier conflict hides content2.80.2%openclawSep 15CRITECVE-2026-57148PraisonAI: hardcoded JWT secret enables auth bypass9.80.6%praisonaiSep 15CRITECVE-2026-57147PraisonAI: hardcoded JWT secret allows auth bypass9.80.8%praisonaiSep 15CRITECVE-2026-57141PraisonAI: codeMode sandbox escape allows unauthenticated RCE9.80.7%praisonaiSep 15CRITECVE-2026-57140PraisonAI: unauthenticated AgentOS API exposes agents9.40.6%praisonaiSep 15CRITECVE-2026-57139PraisonAI: unauthenticated MCP server exposes agent tools9.80.8%praisonaiSep 15CRITECVE-2026-57138PraisonAI: codeMode sandbox escape allows RCE9.90.7%praisonaiSep 15HIGHECVE-2026-57137PraisonAI: approval bypass runs rejected agent tools8.80.5%praisonaiSep 15Frequently 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