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

3,023

AI/ML CVEs Tracked

424

Critical

115

New This Week

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 1321 results — High severity

Severity CVE ID Summary CVSS EPSS Package Date

HIGH CVE-2026-46444 Flowise: missing authz on vector store CRUD ops 8.8 0.3% flowise Jun 8 HIGH CVE-2026-47732 twig/twig: sandbox bypass leaks render context — 0.4% twig/twig Jun 5 HIGH GHSA-wx3m-whqv-xv47 skillctl: path traversal enables credential exfiltration — — skillctl Jun 5 HIGH E CVE-2026-47419 praisonai-platform: IDOR enables cross-workspace agent read/write/delete 8.3 0.3% praisonai-platform Jun 5 HIGH E CVE-2026-10814 Milvus: weak hash allows RBAC grantee impersonation 7.0 0.1% milvus Jun 4 HIGH GHSA-f9rx-7wf7-jr36 Froxlor: 2FA bypass via API grants full account access 8.1 — froxlor/froxlor Jun 3 HIGH E CVE-2026-41234 Froxlor: DNS zone injection via unsanitized TXT record 7.6 0.3% froxlor/froxlor Jun 3 HIGH E CVE-2026-6657 jupyter-server: CORS bypass enables arbitrary code execution 8.8 0.2% jupyter-server Jun 3 HIGH E CVE-2026-4035 MLflow: AI Gateway leaks cloud credentials via env injection 7.7 0.4% mlflow Jun 3 HIGH CVE-2026-31942 LibreChat: IDOR enables cross-user API key hijacking 7.1 0.2% — Jun 2 HIGH CVE-2025-64390 PS4 BD-J: sandbox escape via malformed JAR file 7.4 0.1% — Jun 2 HIGH E CVE-2026-5422 jupyter-server: path traversal exposes sibling dir files 8.1 0.4% jupyter Jun 2 HIGH E CVE-2026-43624 F5-TTS: path traversal enables arbitrary file write 8.2 0.4% — Jun 1 HIGH CVE-2026-38950 AnomalyMatch: RCE via torch.load() unsafe deserialization 7.8 0.1% — Jun 1 HIGH E CVE-2026-10118 Poppler: PDF integer overflow enables heap RCE 7.8 0.3% rhaiis/vllm-spyre-rhel9 Jun 1 HIGH E CVE-2026-47412 praisonai-platform: member can wipe entire workspace 8.1 0.3% praisonai-platform Jun 1 HIGH E CVE-2026-47415 praisonai-platform: IDOR exposes cross-workspace tenant data 8.3 0.3% praisonai-platform Jun 1 HIGH E CVE-2026-47417 praisonai-platform: IDOR enables cross-tenant comment exfil 8.1 0.2% praisonai-platform Jun 1 HIGH E CVE-2026-47418 praisonai-platform: IDOR exposes cross-workspace projects 8.1 0.3% praisonai-platform Jun 1 HIGH E CVE-2026-47409 praisonai-platform: auth bypass enables owner lockout 8.1 0.3% praisonai-platform May 29

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