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 1076 results — has patch 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 HIGH CVE-2026-53813 OpenClaw: path traversal enables RCE via memory-core artifacts 7.8 0.1% openclaw Jun 11 HIGH CVE-2026-53812 OpenClaw: SSRF bypasses private-network access controls 7.7 0.2% openclaw Jun 11 HIGH CVE-2026-53811 OpenClaw: privilege escalation via identity spoofing 8.8 0.3% openclaw Jun 11 HIGH CVE-2026-53810 OpenClaw: extension metadata bypass enables agent RCE 8.8 0.4% openclaw Jun 11 LOW CVE-2026-53809 OpenClaw: policy bypass exposes restricted tool access 3.8 0.1% openclaw Jun 11 HIGH CVE-2026-53806 OpenClaw: shell flag bypass enables RCE in agent exec 8.8 0.4% openclaw Jun 11 HIGH E CVE-2026-11816 Keras: path traversal allows arbitrary file write 8.1 0.6% keras Jun 11 MEDI CVE-2026-47155 vLLM: revision pin bypass loads unreviewed artifacts 6.5 0.2% vllm Jun 10 LOW CVE-2026-47241 net-imap: IMAP command smuggling enables DoS — 0.2% net-imap Jun 9 HIGH CVE-2026-47732 twig/twig: sandbox bypass leaks render context — 0.4% twig/twig Jun 5 HIGH GHSA-wx3m-whqv-xv47 skillctl: path traversal enables credential exfiltration — — skillctl Jun 5 HIGH E CVE-2026-47419 praisonai-platform: IDOR enables cross-workspace agent read/write/delete 8.3 0.3% praisonai-platform Jun 5 MEDI E CVE-2026-47250 mcp-server-kubernetes: flag injection steals K8s tokens 6.1 0.3% mcp-server-kubernetes 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 LOW E CVE-2026-10803 MLflow: weak dataset hash allows integrity bypass 3.6 0.1% mlflow Jun 4 LOW E CVE-2026-10783 Gradio: weak hash exposes audio cache to local users 2.5 0.1% gradio Jun 4 HIGH GHSA-f9rx-7wf7-jr36 Froxlor: 2FA bypass via API grants full account access 8.1 — froxlor/froxlor Jun 3 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