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 2900 results — no patchCVE-2026-32057OpenClaw: auth bypass grants unauthorized agent control access7.10.3%OpenClawMar 21HIGHCVE-2026-32056OpenClaw: RCE via shell env var injection in system.run7.50.6%OpenClawMar 21HIGHCVE-2026-32055OpenClaw: path traversal enables arbitrary file write7.60.3%OpenClawMar 21MEDICVE-2026-32054OpenClaw: symlink traversal enables arbitrary file overwrite6.50.1%OpenClawMar 21MEDICVE-2026-32053OpenClaw: webhook replay bypass corrupts agent call state6.50.4%OpenClawMar 21MEDICVE-2026-32052OpenClaw: command injection via shell-wrapper argv bypass6.40.9%OpenClawMar 21HIGHCVE-2026-32051OpenClaw: auth bypass lets operators invoke owner control-plane8.80.4%OpenClawMar 21LOWCVE-2026-32050OpenClaw: auth bypass allows unauthorized status event injection3.70.2%OpenClawMar 21HIGHCVE-2026-32049OpenClaw: media limit bypass enables memory exhaustion DoS7.50.6%OpenClawMar 21HIGHCVE-2026-32048OpenClaw: sandbox escape via cross-agent spawn bypass7.50.3%OpenClawMar 21MEDICVE-2026-32046OpenClaw: sandbox bypass enables host code execution5.30.3%OpenClawMar 21MEDICVE-2026-32045OpenClaw: auth bypass exposes HTTP gateway routes5.90.4%OpenClawMar 21MEDICVE-2026-32044OpenClaw: archive safety bypass causes DoS in skill install5.50.1%OpenClawMar 21MEDICVE-2026-32043OpenClaw: TOCTOU symlink bypasses command approval guard6.50.1%OpenClawMar 21HIGHCVE-2026-32042OpenClaw: privilege escalation via unpaired device identity8.80.4%OpenClawMar 21HIGHECVE-2026-23536Feast: unauth path traversal leaks any file7.52.5%rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel9Mar 20CRITCVE-2026-22172OpenClaw: WebSocket scope self-elevation grants admin9.90.6%OpenClawMar 20HIGHCVE-2026-33053langflow: IDOR enables unauthorized data access8.80.4%langflowMar 20MEDICVE-2026-32041OpenClaw: auth bypass exposes browser-control RCE6.90.1%OpenClawMar 19MEDICVE-2026-32040OpenClaw: XSS via HTML export mimeType injection4.60.2%OpenClawMar 19Frequently 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