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 1527 results — Medium severityCVE-2026-100712Froxlor: CSRF on GET silently disables 2FA6.50.1%—Sep 26MEDICVE-2026-100654vLLM: out-of-range stop_token_ids crash EngineCore (DoS)6.50.3%vllmSep 26MEDIECVE-2026-100653vLLM: revision pin bypass loads unpinned HF artifacts6.50.3%vllmSep 26MEDIECVE-2026-100651vLLM: prompt-length bypass on disagg endpoint causes DoS6.50.4%vllmSep 26MEDIECVE-2026-100650vLLM: unbounded media fetch enables pre-inference DoS6.50.8%vllmSep 26MEDICVE-2026-100649vLLM: sampler subclass bypass exhausts GPU memory5.30.3%vllmSep 26MEDICVE-2026-100648vLLM: audio size limit bypass enables resource exhaustion5.30.4%vllmSep 26MEDICVE-2026-100633SiYuan: MCP file guard bypass exposes protected files6.50.4%—Sep 26MEDIECVE-2026-100609Flowise: cross-workspace credential IDOR exposes API keys6.80.3%—Sep 26MEDICVE-2026-100604ClawHub: ex-publisher can hijack org skills post-revocation5.40.3%—Sep 26MEDICVE-2026-100603ClawHub: coordinated reports hide skills from catalog5.40.3%openclawSep 26MEDICVE-2026-100602ClawHub: missing authz leaks quarantined skill content6.50.3%openclawSep 26MEDICVE-2026-100601ClawHub: SSRF via DNS rebinding in profile image preview5.30.3%openclawSep 26MEDICVE-2026-100600ClawHub: anonymous API quota exhaustion enables DoS5.30.4%—Sep 26MEDICVE-2026-100595OpenClaw: authorization bypass exposes owner host diagnostics6.50.2%openclawSep 26MEDICVE-2026-100594OpenClaw: authorization bypass exposes owner trajectory exports6.50.2%openclawSep 26MEDICVE-2026-100593OpenClaw: missing owner check on /activation policy changes5.40.1%openclawSep 26MEDICVE-2026-100592OpenClaw: missing owner check lets non-owners toggle memory6.30.2%openclawSep 26MEDICVE-2026-100591OpenClaw: missing owner check on Active Memory toggles6.30.2%openclawSep 26MEDICVE-2026-100590OpenClaw: authorization bypass in /voice set alters config4.30.2%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