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 4330 resultsCVE-2026-4775libtiff: integer overflow causes heap OOB write7.80.6%rhaiis/vllm-spyre-rhel9Mar 24HIGHECVE-2026-33497langflow: Path Traversal enables file access7.519.6%langflowMar 24HIGHECVE-2026-33484langflow: Access Control bypass enables privilege escalation7.55.9%langflowMar 24CRITECVE-2026-33475langflow: security flaw enables exploitation9.13.2%langflowMar 24CRITECVE-2026-33309langflow: Path Traversal enables file access9.913.5%langflowMar 24CRITCVE-2026-32913OpenClaw: auth header leak via cross-origin redirect9.30.3%OpenClawMar 23MEDICVE-2026-27646OpenClaw: sandbox escape via /acp spawn command6.10.1%OpenClawMar 23MEDICVE-2026-27183OpenClaw: shell allowlist bypass via dispatch wrapper depth5.30.1%OpenClawMar 23MEDIECVE-2026-30886AI component: IDOR enables unauthorized data access6.50.3%—Mar 23HIGHECVE-2026-4538AI component: Input Validation flaw enables exploitation7.80.2%—Mar 22MEDICVE-2026-32899OpenClaw: sender-policy bypass injects unauthorized agent events4.30.2%OpenClawMar 21MEDICVE-2026-32898OpenClaw: ACP bypass enables silent tool execution5.40.3%OpenClawMar 21LOWCVE-2026-32897OpenClaw: auth token leak via prompt hash fallback3.70.3%OpenClawMar 21MEDICVE-2026-32896OpenClaw: auth bypass via webhook passwordless fallback4.80.3%OpenClawMar 21MEDICVE-2026-32895OpenClaw: auth bypass circumvents Slack event allowlists5.40.2%OpenClawMar 21LOWCVE-2026-32067OpenClaw: auth bypass enables cross-account pairing reuse3.70.2%OpenClawMar 21MEDICVE-2026-32065OpenClaw: approval bypass enables unauthorized command exec4.80.3%OpenClawMar 21HIGHCVE-2026-32064OpenClaw: unauthenticated VNC access in AI sandbox7.70.5%OpenClawMar 21LOWCVE-2026-32058OpenClaw: approval bypass enables unauthorized agent execution2.60.2%OpenClawMar 21HIGHCVE-2026-32057OpenClaw: auth bypass grants unauthorized agent control access7.10.3%OpenClawMar 21Frequently 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