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
2,404

AI/ML CVEs Tracked

347

Critical

310

New This Week

18

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 1033 results — High severity
Severity CVE ID Summary CVSS EPSS Package Date
HIGH E CVE-2024-39721 Ollama: DoS via /dev/random causes goroutine exhaustion 7.5 2.7% ollama Oct 31 HIGH E CVE-2024-39720 Ollama: OOB read in GGUF parser enables remote DoS 8.2 2.5% ollama Oct 31 HIGH E CVE-2024-39719 Ollama: file existence oracle via api/create errors 7.5 4.1% ollama Oct 31 HIGH CVE-2024-47870 Gradio: race condition enables backend URL hijacking 8.1 0.4% gradio Oct 10 HIGH E CVE-2024-47868 Gradio: path traversal leaks arbitrary server files 7.5 0.8% gradio Oct 10 HIGH CVE-2024-47867 Gradio: no integrity check on FRP binary, supply chain RCE 7.5 0.2% gradio Oct 10 HIGH CVE-2024-47084 Gradio: CORS bypass exposes local instances to credential theft 8.3 0.5% gradio Oct 10 HIGH E CVE-2024-7714 AYS ChatGPT WP Plugin: auth bypass disables AI service 7.5 0.8% — Sep 27 HIGH E CVE-2024-8768 vLLM: unauthenticated DoS via empty completion prompt 7.5 0.7% — Sep 17 HIGH E CVE-2024-5998 LangChain: RCE via FAISS pickle deserialization 7.8 0.4% langchain Sep 17 HIGH CVE-2024-6587 LiteLLM: SSRF leaks OpenAI API key to attacker 7.5 36.9% litellm Sep 13 HIGH E CVE-2024-45848 MindsDB: RCE via eval() injection in ChromaDB INSERT 8.8 0.8% — Sep 12 HIGH E CVE-2024-45436 Ollama: ZIP path traversal exposes host filesystem 7.5 2.6% ollama Aug 29 HIGH CVE-2023-33976 TensorFlow: DoS via upper_bound rank validation crash 7.5 0.4% tensorflow Jul 30 HIGH E CVE-2024-7297 Langflow: mass assignment grants super admin access 8.8 21.3% langflow Jul 30 HIGH E CVE-2024-35199 TorchServe: default gRPC exposure allows unauth inference 8.2 0.6% torchserve Jul 19 HIGH E CVE-2024-21513 langchain-experimental: RCE via eval() in VectorSQL chain 8.5 1.5% langchain-experimental Jul 15 HIGH E CVE-2024-36421 Flowise: CORS wildcard enables file read and data theft 7.5 8.5% flowise Jul 1 HIGH E CVE-2024-36420 Flowise: unauthenticated arbitrary file read via API 7.5 1.8% flowise Jul 1 HIGH E CVE-2024-38459 LangChain: Python REPL code execution without opt-in 7.8 0.2% langchain-experimental 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