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-2025-11844 smolagents: security flaw enables exploitation 5.4 0.3% smolagents Oct 22 MEDI E CVE-2025-60511 Moodle: IDOR enables unauthorized data access 4.3 0.2% — Oct 21 CRIT E CVE-2025-49655 keras: Deserialization enables RCE 9.8 0.7% keras Oct 17 CRIT E CVE-2018-25117 VestaCP: backdoored installer, not an AI/ML CVE — 0.4% Control Panel (CP) Oct 15 HIGH E CVE-2025-34267 Flowise: authenticated RCE via nodevm sandbox escape — 6.1% Flowise Oct 14 HIGH CVE-2025-7707 llama-index: world-writable NLTK dir allows local tampering 7.1 0.2% llama-index Oct 13 CRIT GHSA-m9mp-6x32-5rhg scio/PyTorch: torch.load weights_only bypass RCE — — — Oct 9 CRIT E CVE-2025-61913 Flowise: path traversal in file tools leads to RCE 9.9 12.1% flowise Oct 8 MEDI CVE-2025-61620 vllm: DoS via Jinja template injection in chat API 6.5 0.2% vllm Oct 7 HIGH E CVE-2025-6242 vLLM: SSRF in media loader exposes internal network 7.1 0.2% vllm Oct 7 HIGH E CVE-2025-61784 LLaMA-Factory: SSRF+LFI in multimodal chat API 8.1 0.4% llamafactory Oct 7 HIGH E CVE-2025-59425 vLLM: timing attack enables API key bypass 7.5 0.5% vllm Oct 7 HIGH E CVE-2025-6985 langchain-text-splitters: XXE enables arbitrary file read 7.5 0.6% langchain-text-splitters Oct 6 HIGH E CVE-2025-61687 Flowise: unrestricted file upload enables persistent RCE 8.8 10.3% flowise Oct 6 MEDI E CVE-2025-8917 clearml: path traversal in safe_extract → RCE risk 5.8 0.3% clearml Oct 5 HIGH CVE-2025-0616 Netsis Panel: unauthenticated SQLi enables data exfiltration 8.2 0.3% B2B - Netsis Panel Oct 3 HIGH E CVE-2025-7647 llama-index-core: insecure /tmp dir, model theft risk 7.3 0.1% llama-index-core Sep 27 LOW CVE-2025-59842 JupyterLab: missing noopener enables reverse tabnabbing — 0.2% jupyterlab Sep 26 HIGH E CVE-2025-55560 PyTorch: DoS via sparse/dense tensor Inductor compile 7.5 0.4% pytorch Sep 25 HIGH E CVE-2025-55559 TensorFlow: DoS via Conv2D valid padding crash 7.5 0.2% tensorflow Sep 25

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