AI Threat Alert
AI 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 1579 results — no patch CVE-2026-4963 smolagents: code injection via incomplete sandbox fix 6.3 0.6% smolagents Mar 27 HIGH E CVE-2025-15381 MLflow: broken access control exposes experiment traces 8.1 0.3% mlflow Mar 27 CRIT GHSA-5mg7-485q-xm76 litellm: supply chain attack harvests AI API credentials — — litellm Mar 25 CRIT CVE-2025-33244 NVIDIA: Deserialization enables RCE 9.0 0.6% — Mar 24 MEDI E CVE-2026-33401 Wallos: SSRF allows internal network access 6.5 0.3% — Mar 24 CRIT E CVE-2026-33475 langflow: security flaw enables exploitation 9.1 3.0% langflow Mar 24 CRIT CVE-2026-32913 OpenClaw: auth header leak via cross-origin redirect 9.3 0.3% OpenClaw Mar 23 MEDI CVE-2026-27646 OpenClaw: sandbox escape via /acp spawn command 6.1 0.1% OpenClaw Mar 23 MEDI CVE-2026-27183 OpenClaw: shell allowlist bypass via dispatch wrapper depth 5.3 0.1% OpenClaw Mar 23 MEDI E CVE-2026-30886 AI component: IDOR enables unauthorized data access 6.5 0.3% — Mar 23 HIGH E CVE-2026-4538 AI component: Input Validation flaw enables exploitation 7.8 0.2% — Mar 22 MEDI CVE-2026-32899 OpenClaw: sender-policy bypass injects unauthorized agent events 4.3 0.2% OpenClaw Mar 21 MEDI CVE-2026-32898 OpenClaw: ACP bypass enables silent tool execution 5.4 0.3% OpenClaw Mar 21 LOW CVE-2026-32897 OpenClaw: auth token leak via prompt hash fallback 3.7 0.3% OpenClaw Mar 21 MEDI CVE-2026-32896 OpenClaw: auth bypass via webhook passwordless fallback 4.8 0.2% OpenClaw Mar 21 MEDI CVE-2026-32895 OpenClaw: auth bypass circumvents Slack event allowlists 5.4 0.2% OpenClaw Mar 21 LOW CVE-2026-32067 OpenClaw: auth bypass enables cross-account pairing reuse 3.7 0.2% OpenClaw Mar 21 MEDI CVE-2026-32065 OpenClaw: approval bypass enables unauthorized command exec 4.8 0.3% OpenClaw Mar 21 HIGH CVE-2026-32064 OpenClaw: unauthenticated VNC access in AI sandbox 7.7 0.5% OpenClaw Mar 21 LOW CVE-2026-32058 OpenClaw: approval bypass enables unauthorized agent execution 2.6 0.2% OpenClaw Mar 21 Frequently 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