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
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 4307 results
SeverityCVE IDSummaryCVSSEPSSPackageDate
CRITECVE-2024-23751LlamaIndex: SQL injection in Text-to-SQL feature9.80.7%llamaindexJan 22HIGHECVE-2024-22198Nginx-UI: command injection via settings API7.14.1%github.com/0xJacky/Nginx-UIJan 11HIGHECVE-2024-22197Nginx-UI: authenticated command injection to RCE7.71.5%github.com/0xJacky/Nginx-UIJan 11HIGHECVE-2023-27098TP-Link Tapo: hardcoded creds bypass login auth7.50.4%—Jan 9HIGHECVE-2023-51449Gradio: path traversal grants arbitrary file read7.528.3%gradioDec 22HIGHECVE-2023-7018Transformers: unsafe deserialization enables RCE on load7.80.7%transformersDec 20HIGHECVE-2023-6730HuggingFace Transformers: RCE via unsafe deserialization8.80.9%transformersDec 19HIGHECVE-2023-6909MLflow: path traversal exposes arbitrary files (no auth)7.589.7%mlflowDec 18HIGHECVE-2023-6831MLflow: path traversal allows arbitrary file write8.13.3%mlflowDec 15HIGHECVE-2023-6572Gradio: command injection enables RCE on ML servers8.11.7%gradioDec 14HIGHECVE-2023-6753MLflow: path traversal exposes arbitrary file read/write8.81.1%mlflowDec 13HIGHECVE-2023-6709MLflow: SSTI enables RCE in ML experiment tracking8.80.9%mlflowDec 12MEDIECVE-2023-6568MLflow: reflected XSS via Content-Type header injection6.11.7%mlflowDec 7HIGHECVE-2023-43472MLflow: unauth REST API leaks sensitive ML data7.536.6%mlflowDec 5CRITCVE-2023-48022Ray: unauthenticated RCE via job submission API9.883.9%rayNov 28MEDICVE-2023-48299TorchServe: ZipSlip arbitrary file write via model upload5.30.7%torchserveNov 21CRITECVE-2023-6020Ray: unauthenticated LFI exposes entire filesystem9.314.7%rayNov 16CRITECVE-2023-6014MLflow: auth bypass allows arbitrary account creation9.81.2%mlflowNov 16CRITECVE-2023-6019Ray: unauthenticated RCE via dashboard command injection9.874.6%rayNov 16CRITECVE-2023-6021Ray: LFI allows unauthenticated file read9.337.1%rayNov 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