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 4307 resultsOpenClaw: sandbox path traversal leaks host temp files
CVE-2026-32026OpenClaw: WebSocket auth bypass enables agent hijack
CVE-2026-32025OpenClaw: symlink traversal leaks arbitrary local files
CVE-2026-32024OpenClaw: approval gating bypass enables shell execution
CVE-2026-32023OpenClaw: grep safeBins bypass enables arbitrary file read
CVE-2026-32022OpenClaw: auth bypass via Feishu display name spoofing
CVE-2026-32021OpenClaw: symlink traversal enables arbitrary file read
CVE-2026-32020OpenClaw: SSRF bypass via incomplete IPv4 range validation
CVE-2026-32019OpenClaw: race condition corrupts sandbox registry state
CVE-2026-32018OpenClaw: allowlist bypass enables arbitrary file write
CVE-2026-32017OpenClaw: path bypass allows unauthorized binary execution
CVE-2026-32016OpenClaw: PATH hijack bypasses exec allowlist controls
CVE-2026-32015OpenClaw: metadata spoofing bypasses agent command policies
CVE-2026-32014OpenClaw: symlink traversal enables host file read/write
CVE-2026-32013OpenClaw: pre-auth webhook DoS exhausts parser resources
CVE-2026-32011OpenClaw: safeBins bypass enables arbitrary code execution
CVE-2026-32010OpenClaw: binary hijacking via safeBins path bypass
CVE-2026-32009OpenClaw: file:// bypass enables local file exfiltration
CVE-2026-32008OpenClaw: path traversal enables sandbox file escape
CVE-2026-32007OpenClaw: auth bypass via DM identity confusion in groups
CVE-2026-32006Frequently 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