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 1581 results — no patch CVE-2026-32019 OpenClaw: SSRF bypass via incomplete IPv4 range validation 7.4 0.2% OpenClaw Mar 19 LOW CVE-2026-32018 OpenClaw: race condition corrupts sandbox registry state 3.6 0.1% OpenClaw Mar 19 HIGH CVE-2026-32017 OpenClaw: allowlist bypass enables arbitrary file write 7.1 0.3% OpenClaw Mar 19 HIGH CVE-2026-32016 OpenClaw: path bypass allows unauthorized binary execution 7.8 0.1% OpenClaw Mar 19 HIGH CVE-2026-32015 OpenClaw: PATH hijack bypasses exec allowlist controls 7.8 0.1% OpenClaw Mar 19 HIGH CVE-2026-32014 OpenClaw: metadata spoofing bypasses agent command policies 8.0 0.2% OpenClaw Mar 19 HIGH CVE-2026-32013 OpenClaw: symlink traversal enables host file read/write 8.8 0.6% OpenClaw Mar 19 HIGH CVE-2026-32011 OpenClaw: pre-auth webhook DoS exhausts parser resources 7.5 0.4% OpenClaw Mar 19 MEDI CVE-2026-32010 OpenClaw: safeBins bypass enables arbitrary code execution 6.3 0.3% OpenClaw Mar 19 MEDI CVE-2026-32009 OpenClaw: binary hijacking via safeBins path bypass 5.7 0.1% OpenClaw Mar 19 MEDI CVE-2026-32008 OpenClaw: file:// bypass enables local file exfiltration 6.5 0.4% OpenClaw Mar 19 MEDI CVE-2026-32007 OpenClaw: path traversal enables sandbox file escape 6.8 0.4% OpenClaw Mar 19 LOW CVE-2026-32006 OpenClaw: auth bypass via DM identity confusion in groups 3.1 0.3% OpenClaw Mar 19 MEDI CVE-2026-32005 OpenClaw: auth bypass enables AI agent session poisoning 6.8 0.3% OpenClaw Mar 19 MEDI CVE-2026-32004 OpenClaw: auth bypass exposes protected channel API 6.5 0.3% OpenClaw Mar 19 MEDI CVE-2026-32003 OpenClaw: env var injection enables RCE via allowlist bypass 6.6 0.5% OpenClaw Mar 19 MEDI CVE-2026-32002 OpenClaw: sandbox bypass exfiltrates files via vision API 5.3 0.3% OpenClaw Mar 19 MEDI CVE-2026-32001 OpenClaw: auth bypass enables unauthorized node role injection 5.4 0.3% OpenClaw Mar 19 HIGH E CVE-2026-4424 libarchive: RAR heap OOB read leaks memory in vLLM stacks 7.5 0.9% rhaiis/vllm-cuda-rhel9 Mar 19 HIGH E CVE-2026-33236 nltk: Path Traversal enables file access 8.1 0.4% — Mar 19 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