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
2,376

AI/ML CVEs Tracked

336

Critical

396

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 336 results — Critical severity
Severity CVE ID Summary CVSS EPSS Package Date
CRIT E CVE-2023-36281 LangChain: RCE via malicious JSON prompt template 9.8 2.8% langchain Aug 22 CRIT E CVE-2023-39659 LangChain: RCE via unsanitized PythonAstREPL input 9.8 1.3% langchain Aug 15 CRIT E CVE-2023-38896 LangChain: RCE via unsandboxed LLM code execution 9.8 1.5% langchain Aug 15 CRIT E CVE-2023-38860 LangChain: RCE via unsanitized prompt parameter 9.8 1.2% langchain Aug 15 CRIT E CVE-2023-36095 LangChain PALChain: RCE via unsanitized exec() calls 9.8 1.2% langchain Aug 5 CRIT E CVE-2023-3765 MLflow: path traversal allows arbitrary file read 10.0 70.7% mlflow Jul 19 CRIT E CVE-2023-3686 QuickAI: unauthenticated SQLi exposes OpenAI API keys 9.8 0.4% quickai_openai Jul 16 CRIT E CVE-2023-36188 LangChain: RCE via PALChain unsanitized Python exec 9.8 1.6% langchain Jul 6 CRIT E CVE-2023-36258 LangChain: unauthenticated RCE via code injection 9.8 1.0% langchain Jul 3 CRIT E CVE-2023-34541 LangChain: RCE via unsafe load_prompt deserialization 9.8 0.9% langchain Jun 20 CRIT E CVE-2023-34540 LangChain: RCE via JiraAPIWrapper crafted input 9.8 1.7% langchain Jun 14 CRIT E CVE-2023-34239 Gradio: path traversal + SSRF exposes model files & infra 9.1 0.7% gradio Jun 8 CRIT E CVE-2023-2780 MLflow: path traversal allows arbitrary file read/write 9.8 6.3% mlflow May 17 CRIT E CVE-2023-29374 LangChain: RCE via prompt injection in LLMMathChain 9.8 39.7% langchain Apr 5 CRIT E CVE-2023-25668 TensorFlow: unauthenticated RCE via heap buffer overflow 9.8 0.8% tensorflow Mar 25 CRIT E CVE-2023-25664 TensorFlow: heap overflow in AvgPoolGrad, RCE risk 9.8 0.4% tensorflow Mar 25 CRIT CVE-2023-1177 MLflow: path traversal allows arbitrary file read/write 9.8 69.5% mlflow Mar 24 CRIT E CVE-2023-25823 Gradio: hardcoded SSH key leaks via share=True demos 9.8 0.6% gradio Feb 23 CRIT CVE-2022-41910 TensorFlow Grappler: OOB read crashes or leaks memory 9.1 0.4% tensorflow Dec 6 CRIT E CVE-2022-41902 TensorFlow Grappler: OOB read/crash via crafted model 9.1 0.4% tensorflow Dec 6

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