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 E CVE-2026-47748 stable-diffusion.cpp: OOB read crash via crafted .ckpt file 5.5 0.2% — Jun 16 UNKN CVE-2026-54311 n8n: prototype pollution leaks cross-user workflow data — 0.3% n8n Jun 16 MEDI CVE-2026-54306 n8n: webhook prototype pollution enables confused deputy — 0.3% n8n Jun 16 HIGH CVE-2026-54301 n8n: XSS via CSP bypass steals user sessions — 0.2% n8n Jun 16 MEDI CVE-2026-54308 n8n: unauthed webhook bypass hijacks AI agent workflows — 0.3% n8n Jun 16 HIGH GHSA-hv7x-3x78-gx53 n8n: auth bypass lets read-only users execute workflows 7.4 — n8n Jun 16 UNKN CVE-2026-54313 n8n: MongoDB query injection overwrites arbitrary documents — 0.3% n8n Jun 16 HIGH E CVE-2026-47747 stable-diffusion.cpp: .ckpt heap overflow enables RCE 7.8 0.2% — Jun 16 HIGH E CVE-2026-47750 stable-diffusion.cpp: heap overflow via crafted .ckpt model 7.8 0.2% — Jun 16 UNKN CVE-2026-54310 n8n: SQL injection in Postgres nodes, CVSS 9.9 — 0.4% n8n Jun 16 UNKN CVE-2026-49465 n8n: Git node path traversal bypasses file sandbox — 0.5% n8n Jun 16 UNKN CVE-2026-49444 n8n: Python sandbox escape enables container RCE — 0.4% n8n Jun 16 CRIT E CVE-2026-48746 vllm: auth bypass exposes OpenAI inference API 9.1 1.2% vllm Jun 16 MEDI E CVE-2026-48520 Langflow: unauth file read via Shareable Playground 6.1 0.4% langflow Jun 16 CRIT E CVE-2026-48519 Langflow: unauthenticated RCE via Shareable Playground 9.6 0.8% langflow Jun 16 MEDI E CVE-2026-42867 Langflow: path traversal enables arbitrary file write 6.5 0.3% langflow Jun 16 HIGH CVE-2026-41523 vLLM: assert bypass → RCE via poisoned HuggingFace model 7.5 0.7% vllm Jun 16 HIGH E CVE-2026-33760 Langflow: IDOR exposes cross-user LLM data and deletion 8.8 0.4% langflow Jun 16 MEDI GHSA-gr75-jv2w-4656 LangChain: path traversal exposes files outside sandbox 5.1 — langchain-anthropic Jun 16 HIGH E CVE-2026-54293 NLTK: path traversal leaks arbitrary local files 7.5 0.6% nltk Jun 16

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