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

LangChain PALChain: RCE via unsanitized exec() calls

CVE-2023-36095
9.8
EPSS 1.2%
Code ExecutionPrompt InjectionFrameworkAgent
langchainCWE-943.2K5 ATLAS
CRITICALEXPLOIT AVAILSCANNER

MLflow: path traversal allows arbitrary file read

CVE-2023-3765
10.0
EPSS 67.5%
Data ExtractionData LeakageSupply ChainFrameworkModelTraining Data
mlflow6956 ATLAS
CRITICALEXPLOIT AVAIL

QuickAI: unauthenticated SQLi exposes OpenAI API keys

CVE-2023-3686
9.8
EPSS 0.5%
Data ExtractionAuth BypassAPI
quickai_openai15.6K3 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via PALChain unsanitized Python exec

CVE-2023-36188
9.8
EPSS 1.9%
Code ExecutionSupply ChainData ExtractionFrameworkAgent
langchainCWE-743.2K4 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: unauthenticated RCE via code injection

CVE-2023-36258
9.8
EPSS 1.1%
Code ExecutionSupply ChainData ExtractionFrameworkAgentRAG
langchainCWE-943.2K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via unsafe load_prompt deserialization

CVE-2023-34541
9.8
EPSS 0.9%
Code ExecutionSupply ChainData ExtractionFrameworkAgent
langchain3.2K5 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via JiraAPIWrapper crafted input

CVE-2023-34540
9.8
EPSS 1.7%
Code ExecutionSupply ChainData ExtractionFrameworkAgentPlugin
langchain3.2K6 ATLAS
CRITICALEXPLOIT AVAIL

Gradio: path traversal + SSRF exposes model files & infra

CVE-2023-34239
9.1
EPSS 0.7%
Data ExtractionPrivacy ViolationAuth BypassFrameworkAPI
gradio7355 ATLAS
CRITICALEXPLOIT AVAILSCANNER

MLflow: path traversal allows arbitrary file read/write

CVE-2023-2780
9.8
EPSS 6.4%
Data ExtractionCode ExecutionSupply ChainFrameworkTraining DataModel
mlflow6955 ATLAS
CRITICALEXPLOIT AVAIL

LangChain: RCE via prompt injection in LLMMathChain

CVE-2023-29374
9.8
EPSS 39.7%
Prompt InjectionCode ExecutionFrameworkAgent
langchainCWE-743.2K4 ATLAS
CRITICALEXPLOIT AVAIL

TensorFlow: unauthenticated RCE via heap buffer overflow

CVE-2023-25668
9.8
EPSS 0.8%
Code ExecutionDoSFrameworkInference
tensorflow3.4K4 ATLAS
CRITICALEXPLOIT AVAIL

TensorFlow: heap overflow in AvgPoolGrad, RCE risk

CVE-2023-25664
9.8
EPSS 0.4%
Code ExecutionSupply ChainFrameworkInference
tensorflow3.4K4 ATLAS
CRITICALKEVSCANNER

MLflow: path traversal allows arbitrary file read/write

CVE-2023-1177
9.8
EPSS 69.7%
Data ExtractionCode ExecutionSupply ChainFrameworkModelTraining Data
mlflow6957 ATLAS
CRITICALEXPLOIT AVAIL

Gradio: hardcoded SSH key leaks via share=True demos

CVE-2023-25823
9.8
EPSS 0.6%
Auth BypassData ExtractionPrivacy ViolationFrameworkInference
gradioCWE-7987355 ATLAS
CRITICAL

TensorFlow Grappler: OOB read crashes or leaks memory

CVE-2022-41910
9.1
EPSS 0.4%
Code ExecutionDoSData ExtractionFrameworkInferenceTraining Data
tensorflow3.4K3 ATLAS
CRITICALEXPLOIT AVAIL

TensorFlow Grappler: OOB read/crash via crafted model

CVE-2022-41902
9.1
EPSS 0.5%
DoSData ExtractionFrameworkInference
tensorflowCWE-1253.4K4 ATLAS
CRITICALEXPLOIT AVAIL

PyTorch: RCE via unsafe eval in JIT annotations

CVE-2022-45907
9.8
EPSS 1.3%
Code ExecutionSupply ChainFrameworkInference
pytorchCWE-9426.1K4 ATLAS
CRITICALEXPLOIT AVAIL

Netgear R7000P: buffer overflow via DNS params

CVE-2022-44194
9.8
EPSS 1.5%
Code ExecutionDoSFramework
CRITICALEXPLOIT AVAIL

TensorFlow: heap OOB RCE in FractionalMaxPool op

CVE-2022-41900
9.8
EPSS 0.7%
Code ExecutionDoSFrameworkInference
tensorflow3.4K4 ATLAS
CRITICALEXPLOIT AVAIL

TensorFlow: heap OOB read in candidate sampler op

CVE-2022-41880
9.1
EPSS 0.4%
Data ExtractionDoSCode ExecutionFrameworkInferenceTraining Data
tensorflow3.4K3 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