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 2876 results — no patchCVE-2026-100545OpenClaw: policy bypass lets helper run blocked tools5.30.2%openclawSep 26HIGHCVE-2026-100544OpenClaw: authz bypass in voice-call exposes owner tools8.80.2%openclawSep 26HIGHCVE-2026-100543OpenClaw: config hashes enable offline password cracking7.50.3%openclawSep 26LOWCVE-2026-100542OpenClaw: tar.bz2 skill installer bypasses extraction limits3.10.3%openclawSep 26HIGHCVE-2026-100541OpenClaw Matrix: case-folding auth bypass via ID collision7.50.3%openclawSep 26MEDICVE-2026-100540OpenClaw Feishu: disabled default account still used6.80.2%openclawSep 26LOWCVE-2026-100539OpenClaw: stale memory tool access after hot-disable2.60.2%—Sep 26MEDICVE-2026-100538OpenClaw: tool policy bypass allows local file read6.50.3%openclawSep 26LOWCVE-2026-100537OpenClaw: memory recall bypasses sender tool policy3.10.2%openclawSep 26MEDICVE-2026-100536OpenClaw: path traversal leaks host files via Telegram6.50.4%openclawSep 26HIGHCVE-2026-100535OpenClaw: session-memory flaw enables agent privilege escalation7.50.3%openclawSep 26LOWCVE-2026-100534OpenClaw: authorization bypass cancels unrelated sessions3.10.3%openclawSep 26MEDICVE-2026-100533OpenClaw: Unicode path traversal reads files outside workspace5.30.3%openclawSep 26HIGHCVE-2026-100530OpenClaw: exec approval reuse across directories7.30.2%openclawSep 26MEDICVE-2026-100529OpenClaw: authorization scope widening in file transfer6.40.2%openclawSep 26MEDICVE-2026-100528OpenClaw: credential leak to wrong endpoint on hot reload5.40.2%openclawSep 26MEDICVE-2026-100527OpenClaw: pre-auth DoS in browser relay5.30.3%openclawSep 26MEDICVE-2026-100526OpenClaw Discord: media policy bypass reads local files5.30.3%openclawSep 26MEDICVE-2026-100525OpenClaw: missing scope check exposes Prometheus metrics4.30.2%openclawSep 26HIGHCVE-2026-100532OpenClaw WhatsApp: missing owner check allows account disconnect8.10.3%openclawSep 26Frequently 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