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:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 1961 results — Active exploitation

HIGHEXPLOIT AVAILSCANNER

MLflow: path traversal allows arbitrary file write

CVE-2023-6831

Supply ChainCode ExecutionFrameworkTraining Data

mlflowCWE-226954 ATLAS

HIGHEXPLOIT AVAIL

Gradio: command injection enables RCE on ML servers

CVE-2023-6572

Code ExecutionData ExtractionSupply ChainFrameworkInferenceAPI

gradio7355 ATLAS

HIGHEXPLOIT AVAIL

MLflow: path traversal exposes arbitrary file read/write

CVE-2023-6753

Data ExtractionCode ExecutionSupply ChainFrameworkTraining DataModel

mlflow6955 ATLAS

HIGHEXPLOIT AVAIL

MLflow: SSTI enables RCE in ML experiment tracking

CVE-2023-6709

Code ExecutionSupply ChainData ExtractionFrameworkTraining Data

mlflow6955 ATLAS

MEDIUMEXPLOIT AVAILSCANNER

MLflow: reflected XSS via Content-Type header injection

CVE-2023-6568

Auth BypassData ExtractionFramework

mlflowCWE-796954 ATLAS

HIGHEXPLOIT AVAILSCANNER

MLflow: unauth REST API leaks sensitive ML data

CVE-2023-43472

Data ExtractionData LeakageAuth BypassFrameworkAPITraining Data

mlflow6955 ATLAS

CRITICALKEVSCANNER

Ray: unauthenticated RCE via job submission API

CVE-2023-48022

Code ExecutionAuth BypassFrameworkTraining DataInference

rayCWE-8296426 ATLAS

CRITICALEXPLOIT AVAILSCANNER

Ray: unauthenticated LFI exposes entire filesystem

CVE-2023-6020

Data ExtractionAuth BypassFrameworkTraining DataModel

rayPatch: 2.8.1CWE-5986425 ATLAS

CRITICALEXPLOIT AVAIL

MLflow: auth bypass allows arbitrary account creation

CVE-2023-6014

Auth BypassData ExtractionSupply ChainFrameworkTraining DataModel

mlflow6956 ATLAS

CRITICALEXPLOIT AVAILSCANNER

Ray: LFI allows unauthenticated file read

CVE-2023-6021

Data ExtractionAuth BypassFrameworkInference

rayPatch: 2.8.1CWE-226425 ATLAS

CRITICALEXPLOIT AVAIL

Ray: unauthenticated RCE via dashboard command injection

CVE-2023-6019

Code ExecutionAuth BypassSupply ChainFrameworkInferenceTraining Data

rayPatch: 2.8.1CWE-786426 ATLAS

CRITICALEXPLOIT AVAILSCANNER

MLflow: unauth file overwrite enables model poisoning

CVE-2023-6018

Code ExecutionModel PoisoningSupply ChainFrameworkModelTraining Data

mlflow6955 ATLAS

HIGHEXPLOIT AVAIL

MLflow: unauthenticated arbitrary file write via PUT

CVE-2023-6015

Supply ChainCode ExecutionModel PoisoningFrameworkModelTraining Data

mlflow6956 ATLAS

CRITICALEXPLOIT AVAIL

MLeap: zip slip in model loading enables RCE

CVE-2023-5245

Supply ChainCode ExecutionFrameworkModel

HIGHEXPLOIT AVAIL

LangChain: prompt injection triggers SSRF via URL fetch

CVE-2023-32786

Prompt InjectionData ExtractionFrameworkAgent

langchainCWE-743.2K5 ATLAS

LangChain: SSRF in URL loader exposes internal network

CVE-2023-46229

Data ExtractionAuth BypassFrameworkRAG

langchainCWE-9183.2K4 ATLAS

LangChain: RCE bypass via __import__ in PAL chain

CVE-2023-44467

Code ExecutionAuth BypassFrameworkAgent

langchain_experimental3.2K4 ATLAS

CRITICALKEVSCANNER

TorchServe: SSRF + RCE via unrestricted model URL loading

CVE-2023-43654

Code ExecutionSupply ChainData ExtractionFrameworkInferenceModel

torchserve26.1K5 ATLAS

CRITICALEXPLOIT AVAIL

LangChain: RCE via numexpr evaluate injection

CVE-2023-39631

Code ExecutionSupply ChainFrameworkAgentPlugin

langchainCWE-943.2K5 ATLAS

CRITICALEXPLOIT AVAIL

LangChain: RCE via malicious JSON prompt template

CVE-2023-36281

Code ExecutionSupply ChainFrameworkAgent

langchainCWE-943.2K4 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