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 1432 results — Active exploitation
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2026-47399 praisonai-platform: IDOR breaks workspace tenant isolation 8.8 0.3% praisonai-platform May 29 CRIT E CVE-2026-47407 praisonai-platform: IDOR enables cross-tenant agent hijack — 0.2% praisonai-platform May 29 MEDI E CVE-2026-47408 praisonai-platform: IDOR exposes cross-tenant activity logs 6.5 0.2% praisonai-platform May 29 HIGH E CVE-2026-47397 PraisonAI: arbitrary file write via hidden webpage metadata — 0.4% PraisonAI May 29 CRIT E CVE-2026-47391 PraisonAI: Unauth RCE via A2A eval injection 9.8 0.8% PraisonAI May 29 UNKN E CVE-2026-47394 PraisonAI: MCP path traversal exfiltrates host credentials — 0.4% PraisonAI May 29 CRIT E CVE-2026-47392 praisonaiagents: RCE via Python sandbox bypass 9.9 0.6% PraisonAI May 29 MEDI E CVE-2026-47395 PraisonAI: SSRF via @url mention exposes localhost services 5.5 0.1% PraisonAI May 29 CRIT E CVE-2026-47393 PraisonAI: auth bypass in deployed API exposes LLM + tools 9.8 0.4% PraisonAI May 29 CRIT E CVE-2026-47396 PraisonAI: fail-open auth exposes remote agent control API 9.8 0.3% PraisonAI May 29 MEDI E CVE-2026-47390 PraisonAI: SSRF bypass via loopback alias encodings 5.5 0.2% PraisonAI May 29 HIGH E CVE-2026-47398 PraisonAI: RCE via ungated exec_module in agent config 8.1 0.3% PraisonAI May 29 MEDI E CVE-2026-47213 BoxLite: sandbox timeout bypass enables DoS via SIGALRM 6.5 0.3% boxlite 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 MEDI E CVE-2026-46526 local-deep-research: SSRF via URL parser differential bypass 5.0 0.2% local-deep-research May 28 UNKN E CVE-2026-4944 vllm: trust_remote_code bypass enables RCE via HuggingFace — 0.7% vllm May 28 CRIT E CVE-2026-25879 langroid: Prompt-to-SQL injection enables RCE on DB host 9.8 0.6% langroid May 27 MEDI E CVE-2026-48545 Gradio: cookie injection hijacks cross-Space sessions 6.8 0.4% gradio May 27 HIGH E CVE-2026-7528 Langflow: DoS via uncontrolled resource consumption 7.5 0.3% langflow May 27

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