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 848 results — Medium severity CVE-2026-50634 Apache CXF: JWS signature bypass exposes JAX-RS APIs 6.5 0.3% — Jun 12 MEDI CVE-2026-53818 OpenClaw: MCP loopback auth bypass enables policy evasion 6.6 0.1% OpenClaw Jun 11 MEDI CVE-2026-53815 OpenClaw: auth bypass exposes restricted channel messages 6.5 0.2% OpenClaw Jun 11 MEDI CVE-2026-53808 OpenClaw: approval bypass enables unauthorized skill changes 6.5 0.2% OpenClaw Jun 11 MEDI CVE-2026-3341 Langflow: SSRF exposes internal ML infrastructure 5.4 0.1% langflow Jun 11 MEDI E CVE-2026-46642 draw.io: stored XSS executes JS via crafted diagram file 6.1 0.2% — Jun 10 MEDI CVE-2026-20258 Splunk: stored XSS hijacks dashboards via HTML panel 5.4 0.2% — Jun 10 MEDI CVE-2026-47155 vLLM: revision pin bypass loads unreviewed artifacts 6.5 0.1% vllm Jun 10 MEDI CVE-2026-46443 Flowise: stored credentials exposed via API filter bug 6.5 0.3% flowise Jun 8 MEDI E CVE-2026-47250 mcp-server-kubernetes: flag injection steals K8s tokens 6.1 0.3% mcp-server-kubernetes Jun 5 MEDI E CVE-2026-11326 OpenAI Atlas: XSS enables browser history exfiltration — 0.2% — Jun 5 MEDI CVE-2026-8462 OpenMeter: SQL injection leaks all-tenant metering data — 0.0% github.com/openmeterio/openmeter Jun 4 MEDI E CVE-2026-10804 Streamlit: weak hash enables cache integrity bypass 4.7 0.1% streamlit Jun 4 MEDI E CVE-2026-10548 hermes-agent: auth bypass exposes Anthropic API credentials 5.3 0.1% — Jun 2 MEDI CVE-2026-28511 eLabFTW: IDOR exposes restricted resource titles 4.3 0.2% — Jun 1 MEDI CVE-2026-43625 CodexBar: session cookie leak via HTTP redirect 5.9 0.2% — Jun 1 MEDI CVE-2026-47411 PraisonAI: auth bypass allows workspace settings injection 6.5 0.0% praisonai-platform Jun 1 MEDI E CVE-2026-10166 Edimax BR-6478AC: RCE via command injection in Wi-Fi handler 6.3 1.1% — May 31 MEDI E CVE-2026-10127 Edimax BR-6478AC: RCE via rootAPmac command injection 6.3 1.3% — May 30 MEDI CVE-2026-47408 praisonai-platform: IDOR exposes cross-tenant activity logs 6.5 0.0% praisonai-platform May 29 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