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
3,021

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 3021 results
Severity CVE ID Summary CVSS EPSS Package Date
MEDI CVE-2026-46032 Linux Kernel KVM: nSVM VMEXIT host state corruption 5.5 0.1% — May 27 MEDI CVE-2026-45973 Linux mlx5: RDMA hang DoS on AI training clusters 5.5 0.2% — May 27 MEDI CVE-2026-45907 Linux mlx5e: deadlock DoS in Mellanox NIC recovery paths 5.5 0.1% — May 27 MEDI CVE-2026-3676 IBM Db2 APM: DoS via query special element injection 6.5 0.4% — May 27 UNKN CVE-2026-44176 Kirby CMS: auth bypass exposes restricted page drafts — 0.2% getkirby/cms May 26 UNKN CVE-2026-44175 Kirby CMS: stored XSS in list field enables session hijack — 0.3% getkirby/cms May 26 HIGH CVE-2026-44174 Kirby: unsafe reflection allows privilege escalation — 0.3% getkirby/cms May 26 HIGH CVE-2026-24162 NVIDIA Transformers4Rec: deserialization RCE 7.8 0.4% — May 26 MEDI E CVE-2026-9540 vllm: unauthenticated DoS in OpenAI-compatible serving path 5.3 0.4% vllm May 26 MEDI CVE-2026-41863 Spring AI: path traversal via LLM-chosen filenames 6.5 0.4% org.springframework.ai:spring-ai-anthropic May 26 HIGH CVE-2026-4372 transformers: config.json RCE bypasses trust_remote_code 7.8 0.5% transformers May 26 MEDI E CVE-2026-9468 cline-mcp-memory-bank: path traversal in memory init 6.3 0.3% — May 25 MEDI E CVE-2018-25378 Notebook Pro: DoS via oversized notebook name input 6.2 0.1% — May 25 CRIT E CVE-2026-2651 MLflow: auth bypass on artifact uploads enables RCE 9.0 0.3% mlflow/mlflow May 25 CRIT E CVE-2026-46695 Boxlite: read-only bypass enables host code execution 10.0 0.3% boxlite-cli May 21 HIGH E CVE-2026-47102 LiteLLM: privilege escalation to proxy_admin via /user/update 8.8 0.7% litellm May 21 HIGH E CVE-2026-47101 LiteLLM: RBAC bypass enables proxy admin escalation 8.8 0.7% litellm May 21 HIGH E CVE-2026-46519 mcp-server-kubernetes: auth bypass enables full cluster RCE 8.8 0.4% mcp-server-kubernetes May 21 HIGH E CVE-2026-46517 LMDeploy: hardcoded trust_remote_code enables RCE 7.8 0.1% lmdeploy May 21 HIGH CVE-2026-8596 SageMaker SDK: cleartext HMAC key enables model artifact RCE 7.2 0.4% sagemaker May 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