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
3,591

AI/ML CVEs Tracked

481

Critical

96

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 2346 results — no patch
Severity CVE ID Summary CVSS EPSS Package Date
MEDI CVE-2026-72770 n8n: path traversal in Git node bypasses repo sandbox 6.5 0.5% n8n Aug 11 UNKN CVE-2026-72769 n8n: prototype pollution in VM engine crashes process — 0.3% n8n Aug 11 HIGH CVE-2026-72768 n8n: SSRF bypass in MCP Client node exposes internal hosts 8.3 0.2% n8n Aug 11 UNKN CVE-2026-72767 n8n: Git node RCE via malicious repo hooks — 0.5% n8n Aug 11 HIGH CVE-2026-72766 n8n: Send Email node type confusion enables SSRF, LFI 7.5 0.3% n8n Aug 11 CRIT CVE-2026-72765 n8n: expression sandbox escape leads to RCE 9.9 0.4% n8n Aug 11 UNKN CVE-2026-72764 n8n: module cache poisoning breaks multi-user isolation — 0.4% n8n Aug 11 MEDI CVE-2026-72763 n8n: Editor role bypasses credential ACL via sub-workflow 6.5 0.2% n8n Aug 11 UNKN CVE-2026-72762 n8n: arbitrary file write via Edit Image node format param — 0.3% n8n Aug 11 HIGH CVE-2026-72750 n8n: SQL injection via Snowflake node Execute Query 8.8 0.3% n8n Aug 11 MEDI CVE-2026-72749 n8n: prototype pollution DoS via Edit Fields node 6.5 0.3% n8n Aug 11 MEDI CVE-2026-72785 Craft CMS: read-only role can restructure categories 4.3 0.2% — Aug 11 MEDI E CVE-2026-14549 Ray Enterprise Translation WP plugin: broken access control 4.3 0.2% Ray Enterprise Translation Aug 11 MEDI E CVE-2026-14548 Ray Translation WP: Subscribers can hijack API token 6.5 0.2% Ray Enterprise Translation Aug 11 HIGH CVE-2026-18950 odh-dashboard: unvalidated roleRef enables cluster-admin 8.8 0.4% rhoai/odh-mod-arch-mlflow-rhel9 Aug 10 HIGH CVE-2026-18949 ODH Dashboard: SA token abuse escalates to cluster-admin 8.8 0.4% rhoai/odh-mod-arch-mlflow-rhel9 Aug 10 CRIT CVE-2026-18948 Feast: insecure UDF deserialization enables RCE 9.9 0.7% rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 Aug 10 HIGH CVE-2026-18947 Feast: authz bypass in /materialize triggers DoS 8.5 0.4% rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 Aug 10 MEDI CVE-2026-18942 Feast operator: code injection escalates to cluster admin 5.5 0.3% rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 Aug 10 HIGH CVE-2026-18941 Feast: no-auth default enables RCE via malicious UDF 7.7 0.6% rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 Aug 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