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

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 533 results — Critical severity
CRITICALEXPLOIT AVAIL

MLflow: XSS in recipe runner enables Jupyter RCE

CVE-2024-27133
9.6
EPSS 0.7%
Code ExecutionSupply ChainFramework
mlflow6955 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: XSS in recipes enables client-side RCE

CVE-2024-27132
9.6
EPSS 0.9%
Code ExecutionSupply ChainData ExtractionFrameworkTraining Data
mlflow6955 ATLAS
CRITICALEXPLOIT AVAIL

Gradio: unauthenticated LFI exposes full server filesystem

CVE-2024-0964
9.4
EPSS 1.0%
Data ExtractionData LeakageAuth BypassFrameworkInferenceAPI
gradioCWE-227355 ATLAS
CRITICALEXPLOIT AVAIL

Nginx-UI: arbitrary file write via cert import leads to RCE

CVE-2024-23827
9.8
EPSS 0.7%
Code ExecutionAPI
github.com/0xJacky/Nginx-UIPatch: 1.9.10-0.20240128060047-8581bdd3c6f4CWE-221.8K2 ATLAS
CRITICALEXPLOIT AVAIL

LlamaIndex: SQL injection in Text-to-SQL feature

CVE-2024-23751
9.8
EPSS 0.7%
Code ExecutionData ExtractionPrompt InjectionFrameworkAgent
llamaindexCWE-895 ATLAS
CRITICALKEVSCANNER

Ray: unauthenticated RCE via job submission API

CVE-2023-48022
9.8
EPSS 83.9%
Code ExecutionAuth BypassFrameworkTraining DataInference
rayCWE-8296426 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Ray: unauthenticated LFI exposes entire filesystem

CVE-2023-6020
9.3
EPSS 14.7%
Data ExtractionAuth BypassFrameworkTraining DataModel
rayPatch: 2.8.1CWE-5986425 ATLAS
CRITICALEXPLOIT AVAIL

MLflow: auth bypass allows arbitrary account creation

CVE-2023-6014
9.8
EPSS 1.2%
Auth BypassData ExtractionSupply ChainFrameworkTraining DataModel
mlflow6956 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Ray: LFI allows unauthenticated file read

CVE-2023-6021
9.3
EPSS 37.1%
Data ExtractionAuth BypassFrameworkInference
rayPatch: 2.8.1CWE-226425 ATLAS
CRITICALEXPLOIT AVAIL

Ray: unauthenticated RCE via dashboard command injection

CVE-2023-6019
9.8
EPSS 74.6%
Code ExecutionAuth BypassSupply ChainFrameworkInferenceTraining Data
rayPatch: 2.8.1CWE-786426 ATLAS
CRITICALEXPLOIT AVAILSCANNER

MLflow: unauth file overwrite enables model poisoning

CVE-2023-6018
9.8
EPSS 47.9%
Code ExecutionModel PoisoningSupply ChainFrameworkModelTraining Data
mlflow6955 ATLAS
CRITICALEXPLOIT AVAIL

MLeap: zip slip in model loading enables RCE

CVE-2023-5245
9.8
EPSS 1.2%
Supply ChainCode ExecutionFrameworkModel
3 ATLAS
CRITICAL

LangChain: prompt injection → SQL RCE (CVSS 9.8)

CVE-2023-32785
9.8
Prompt InjectionCode ExecutionData ExtractionFrameworkAgent
langchainPatch: 0.0.247CWE-743.2K5 ATLAS
CRITICALKEV

LangChain: RCE bypass via __import__ in PAL chain

CVE-2023-44467
9.8
EPSS 1.0%
Code ExecutionAuth BypassFrameworkAgent
langchain_experimental3.2K4 ATLAS
CRITICALKEVSCANNER

TorchServe: SSRF + RCE via unrestricted model URL loading

CVE-2023-43654
9.8
EPSS 42.5%
Code ExecutionSupply ChainData ExtractionFrameworkInferenceModel
torchserve26.1K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via numexpr evaluate injection

CVE-2023-39631
9.8
EPSS 1.6%
Code ExecutionSupply ChainFrameworkAgentPlugin
langchainCWE-943.2K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via malicious JSON prompt template

CVE-2023-36281
9.8
EPSS 3.4%
Code ExecutionSupply ChainFrameworkAgent
langchainCWE-943.2K4 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via unsanitized PythonAstREPL input

CVE-2023-39659
9.8
EPSS 1.5%
Code ExecutionPrompt InjectionFrameworkAgentPlugin
langchainCWE-743.2K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via unsandboxed LLM code execution

CVE-2023-38896
9.8
EPSS 1.8%
Code ExecutionPrompt InjectionData ExtractionFrameworkAgentAPI
langchainCWE-743.2K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via unsanitized prompt parameter

CVE-2023-38860
9.8
EPSS 1.4%
Code ExecutionPrompt InjectionData ExtractionFrameworkAgent
langchainCWE-943.2K7 ATLAS

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