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 E CVE-2026-47414 praisonai-platform: IDOR cross-workspace label tampering 7.6 0.2% praisonai-platform May 29 HIGH E CVE-2026-47406 praisonai-platform: IDOR enables cross-workspace data poisoning 8.1 0.2% praisonai-platform May 29 HIGH E CVE-2026-47405 PraisonAI Platform: member self-promotes to workspace owner 8.8 0.3% praisonai-platform May 29 HIGH E CVE-2026-47399 praisonai-platform: IDOR breaks workspace tenant isolation 8.8 0.3% praisonai-platform May 29 HIGH CVE-2026-48169 praisonai-platform: IDOR allows full workspace takeover 8.8 0.3% praisonai-platform May 29 HIGH E CVE-2026-47397 PraisonAI: arbitrary file write via hidden webpage metadata — 0.4% PraisonAI May 29 HIGH E CVE-2026-47398 PraisonAI: RCE via ungated exec_module in agent config 8.1 0.3% PraisonAI May 29 HIGH CVE-2026-35674 OpenClaw: scope bypass enables full agent admin takeover 8.8 0.3% openclaw May 29 HIGH CVE-2026-35630 OpenClaw: auth bypass enables unauthorized agent approval 8.0 0.2% openclaw May 29 HIGH CVE-2026-32905 OpenClaw: auth bypass enables persistent device enrollment 8.3 0.2% openclaw May 29 HIGH E CVE-2026-41236 Froxlor: symlink-following grants customer root SSH access 8.8 0.4% froxlor/froxlor May 29 HIGH E CVE-2026-41235 Froxlor: shell whitelist bypass grants host shell access — 0.2% froxlor/froxlor May 29 HIGH CVE-2026-46181 Linux kernel RDMA/mlx4: RCU race may crash ML training nodes 7.8 0.1% — May 28 HIGH CVE-2026-46178 Linux mlx4 RDMA: resource leak on SRQ creation error 7.8 0.1% — May 28 HIGH CVE-2026-46176 Linux mlx5 RDMA: use-after-free in SRQ init path 7.8 0.1% — May 28 HIGH CVE-2026-45368 Kirby CMS: Stored XSS via javascript: URI scheme bypass — 0.3% getkirby/cms May 27 HIGH E CVE-2026-7528 Langflow: DoS via uncontrolled resource consumption 7.5 0.3% langflow May 27 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 HIGH CVE-2026-4372 transformers: config.json RCE bypasses trust_remote_code 7.8 0.5% transformers May 26

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