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.

Sources
Each CVE is enriched with
  • CVSS severity
  • EPSS exploit probability
  • Exploitation confidence
  • AI-component classification
  • Compliance mappings
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

In CISA KEV

Sort: Date CVSS EPSS KEV first Most exploited
Filter: All Critical High Medium KEV only Active exploitation Has patch No patch

Latest AI Security Threats

Showing 20 of 3590 results
Severity CVE ID Summary CVSS EPSS Package Date
HIGH CVE-2026-6485 InsydeH2O UEFI: BIOS Shell allows Secure Boot bypass 8.2 0.1% InsydeH2O Sep 9 MEDI CVE-2026-86995 n8n Git node: config injection leaks local files — 0.3% n8n Sep 8 MEDI CVE-2026-86994 n8n: broken authZ leaks workflow IDs to any member — 0.2% n8n Sep 8 MEDI CVE-2026-86993 n8n: cross-project credential theft via Log Streaming — 0.3% n8n Sep 8 MEDI CVE-2026-86085 n8n: missing scope check leaks project member emails — 0.3% n8n Sep 8 MEDI CVE-2026-86084 n8n: stale OIDC endpoint bypasses disabled SSO — 0.3% n8n Sep 8 HIGH CVE-2026-86083 n8n: code injection via legacy expression engine — 0.4% n8n Sep 8 HIGH CVE-2026-86082 n8n: OpenAI node leaks API key via SSRF bypass — 0.2% n8n Sep 8 HIGH CVE-2026-86081 n8n: ReDoS via Git node clone freezes instance — 0.3% n8n Sep 8 MEDI CVE-2026-86080 n8n: GitHub webhook signature bypass on 422 retry — 0.2% n8n Sep 8 MEDI CVE-2026-86079 n8n: path traversal in Elasticsearch node leaks data — 0.3% n8n Sep 8 MEDI CVE-2026-86078 n8n: prototype pollution in AI workflow summary — 0.3% n8n Sep 8 MEDI CVE-2026-86077 n8n: chat token replay bypasses HITL approval gates — 0.3% n8n Sep 8 HIGH CVE-2026-86076 n8n: expression sandbox escape enables RCE — 0.4% n8n Sep 8 HIGH CVE-2026-86075 n8n: unauth OAuth DCR fields exhaust DB storage — 0.3% n8n Sep 8 UNKN CVE-2026-86996 n8n: Agent tool bypasses workflow caller restriction — 0.2% n8n Sep 8 HIGH E CVE-2026-84452 winml-cli: RCE via wildcard CORS + trust-remote-code — 0.9% winml-cli Sep 8 HIGH GHSA-j95f-988m-3j2f tiptap: ReDoS in Markdown attribute parsers — — @tiptap/core Sep 8 MEDI CVE-2026-85981 Auth0 AD/LDAP Connector: unauth local panel leaks AD creds 6.7 0.1% — Sep 8 HIGH E CVE-2026-80206 NLTK tgrep ReDoS: single request hangs Python process — 0.3% nltk Sep 8

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