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 1580 results — no patch CVE-2026-35669 OpenClaw: privilege escalation via plugin scope bypass 8.8 0.3% OpenClaw Apr 10 HIGH CVE-2026-35668 OpenClaw: sandbox path traversal exposes agent secrets 7.7 0.4% OpenClaw Apr 10 MEDI CVE-2026-35667 OpenClaw: SIGKILL bypass skips security-sensitive cleanup 6.1 0.1% OpenClaw Apr 10 HIGH CVE-2026-35666 OpenClaw: allowlist bypass enables arbitrary command exec 8.8 0.4% OpenClaw Apr 10 MEDI CVE-2026-35665 OpenClaw: pre-auth resource exhaustion via Feishu webhook DoS 5.3 0.3% OpenClaw Apr 10 MEDI CVE-2026-35664 OpenClaw: auth bypass enables unauthorized callback injection 5.3 0.3% OpenClaw Apr 10 HIGH CVE-2026-35663 OpenClaw: privilege escalation to admin via backend reconnect 8.8 0.3% OpenClaw Apr 10 MEDI CVE-2026-35662 OpenClaw: missing auth enables agent scope bypass 4.3 0.2% OpenClaw Apr 10 MEDI CVE-2026-35661 OpenClaw: auth bypass mutates AI agent session state 5.3 0.3% OpenClaw Apr 10 HIGH CVE-2026-35660 OpenClaw: auth bypass allows admin session hijacking 8.1 0.3% OpenClaw Apr 10 MEDI CVE-2026-35659 OpenClaw: DNS-SD metadata hijacks CLI routing 4.6 0.1% OpenClaw Apr 10 MEDI CVE-2026-35658 OpenClaw: sandbox bypass exposes host filesystem reads 6.5 0.3% OpenClaw Apr 10 MEDI CVE-2026-35656 OpenClaw: auth bypass via X-Forwarded-For spoofing 6.5 0.3% OpenClaw Apr 10 MEDI CVE-2026-35655 OpenClaw: identity spoofing bypasses agent safety checks 5.7 0.2% OpenClaw Apr 10 MEDI CVE-2026-35654 OpenClaw: auth bypass on Teams feedback invoke 5.3 0.2% OpenClaw Apr 10 HIGH CVE-2026-35653 OpenClaw: auth bypass enables agent profile destruction 8.1 0.6% OpenClaw Apr 10 MEDI CVE-2026-35652 OpenClaw: auth bypass enables unauthorized action execution 6.5 0.4% OpenClaw Apr 10 HIGH CVE-2026-35650 OpenClaw: env var override bypass enables code execution 7.5 0.5% OpenClaw Apr 10 MEDI CVE-2026-35649 OpenClaw: access control bypass via allowlist reconciliation 6.5 0.3% OpenClaw Apr 10 LOW CVE-2026-35648 OpenClaw: policy bypass via stale queued node actions 3.7 0.2% OpenClaw Apr 10 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