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 848 results — Medium severity GHSA-664h-gpgq-h6xx n8n: viewer role can start/cancel/delete eval workflow runs 5.4 — n8n Jun 17 MEDI CVE-2026-12491 vLLM: image metadata mishandling corrupts multimodal inputs 4.8 0.2% rhaiis/vllm-cpu-rhel9 Jun 17 MEDI CVE-2026-54314 n8n: decompression bomb DoS via public webhook — 0.3% n8n Jun 16 MEDI GHSA-h3jj-5f3v-3685 n8n: read-only users can trigger workflow execution via API 6.4 — n8n Jun 16 MEDI GHSA-jwm3-qcfw-c5pp n8n: AST bypass leaks env vars in Python Task Runner 5.0 — n8n Jun 16 MEDI CVE-2026-54303 n8n: reflected XSS in trigger nodes enables session hijack — 0.3% n8n Jun 16 MEDI CVE-2026-48776 LangGraph SDK: path traversal bypasses proxy-layer authz 4.2 0.2% langchain-ai Jun 16 MEDI CVE-2026-53862 OpenClaw: bootstrap token replay enables scope escalation 4.2 0.1% openclaw Jun 16 MEDI CVE-2026-53861 OpenClaw: allowlist bypass enables arbitrary shell exec 6.6 0.2% openclaw Jun 16 MEDI CVE-2026-53860 OpenClaw: sender allowlist bypass via conversation metadata 4.2 0.2% openclaw Jun 16 MEDI CVE-2026-53859 OpenClaw: SSRF blocklist bypass via trailing-dot 6.5 0.2% openclaw Jun 16 MEDI CVE-2026-53856 OpenClaw: insecure permissions expose agent config 5.5 0.1% openclaw Jun 16 MEDI CVE-2026-53854 OpenClaw: privilege escalation via channel auth wildcard 6.5 0.2% openclaw Jun 16 MEDI CVE-2026-53852 OpenClaw: scope bypass allows unauthorized device access 5.4 0.2% openclaw Jun 16 MEDI CVE-2026-53851 OpenClaw: Slack reaction bypass triggers agent pipeline 5.3 0.2% openclaw Jun 16 MEDI CVE-2026-53850 OpenClaw: auth bypass allows unauthorized focus state change 5.5 0.1% openclaw Jun 16 MEDI CVE-2026-53848 OpenClaw: exec allowlist bypass via command wrappers 4.3 0.2% openclaw Jun 16 MEDI CVE-2026-53847 OpenClaw: privilege escalation via write scope bypass 5.4 0.2% openclaw Jun 16 MEDI CVE-2026-53845 OpenClaw: hook bypass enables audit/policy evasion 4.3 0.2% openclaw Jun 16 MEDI CVE-2026-53844 OpenClaw: auth bypass exposes cross-session agent memory 6.5 0.2% openclaw Jun 16 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