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-2026-32039OpenClaw: auth bypass grants privileged tool access5.90.2%OpenClawMar 19CRITCVE-2026-32038OpenClaw: sandbox bypass enables container lateral movement9.80.3%OpenClawMar 19MEDICVE-2026-32037OpenClaw: SSRF bypass via MSTeams redirect chain6.00.2%OpenClawMar 19MEDICVE-2026-32036OpenClaw: auth bypass via encoded path traversal in gateway6.50.5%OpenClawMar 19MEDICVE-2026-32035OpenClaw: auth bypass grants owner-level tool access5.90.1%OpenClawMar 19HIGHCVE-2026-32034OpenClaw: auth bypass enables high-privilege agent control8.10.4%OpenClawMar 19MEDICVE-2026-32033OpenClaw: path traversal leaks files outside workspace6.50.4%OpenClawMar 19HIGHCVE-2026-32032OpenClaw: SHELL env var injection enables local RCE7.80.1%OpenClawMar 19MEDICVE-2026-32031OpenClaw: auth bypass in plugin channel gateway4.80.2%OpenClawMar 19HIGHCVE-2026-32030OpenClaw: path traversal exposes host files via SCP7.50.4%OpenClawMar 19MEDICVE-2026-32029OpenClaw: IP spoofing bypasses rate-limiting controls5.30.2%OpenClawMar 19MEDICVE-2026-32028OpenClaw: auth bypass enables unauthorized agent execution5.30.2%OpenClawMar 19MEDICVE-2026-32027OpenClaw: authorization bypass in group sender allowlist6.50.3%OpenClawMar 19MEDICVE-2026-32026OpenClaw: sandbox path traversal leaks host temp files6.50.4%OpenClawMar 19HIGHCVE-2026-32025OpenClaw: WebSocket auth bypass enables agent hijack7.50.3%OpenClawMar 19MEDICVE-2026-32024OpenClaw: symlink traversal leaks arbitrary local files5.50.3%OpenClawMar 19HIGHECVE-2026-32023OpenClaw: approval gating bypass enables shell execution7.10.3%OpenClawMar 19MEDICVE-2026-32022OpenClaw: grep safeBins bypass enables arbitrary file read6.50.3%OpenClawMar 19MEDICVE-2026-32021OpenClaw: auth bypass via Feishu display name spoofing6.50.2%OpenClawMar 19LOWCVE-2026-32020OpenClaw: symlink traversal enables arbitrary file read3.30.1%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