AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

New This Week

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 167 results — Critical severity, no patch

CRITICAL EXPLOIT AVAIL

n8n-workflows: path traversal in download_workflow endpoint

Data Extraction Auth Bypass Code Execution Agent Framework API

fastapi 16 5 ATLAS

CRITICAL EXPLOIT AVAIL

Azure OpenAI: SSRF EoP, no auth required (CVSS 10)

Auth Bypass Data Extraction Privacy Violation API Inference

azure_openai 13.8K 6 ATLAS

CRITICAL EXPLOIT AVAIL

ChatGLM-Webui: arbitrary file read, no auth required

Data Extraction Auth Bypass Framework API

langchain-chatglm-webui 2.6K 5 ATLAS

CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated SSRF via file upload URLs

Supply Chain Data Extraction Auth Bypass Framework Inference API

bentoml CWE-918 23 5 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain GmailToolkit: indirect prompt injection to RCE

Prompt Injection Code Execution Data Extraction Framework Agent Plugin

6 ATLAS

CRITICAL EXPLOIT AVAIL

smolagents: sandbox escape enables unauthenticated RCE

Code Execution Supply Chain Data Leakage Framework Agent

smolagents CWE-94 88 5 ATLAS

CRITICAL EXPLOIT AVAIL

Langchain-Chatchat: path traversal in KB upload

Code Execution Data Extraction Supply Chain Framework RAG

langchain-chatchat CWE-22 2.6K 5 ATLAS

CRITICAL EXPLOIT AVAIL

LLaMA-Factory: RCE via unsafe checkpoint deserialization

Code Execution Supply Chain Framework Model

llamafactory CWE-94 1 6 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain RequestsToolkit: SSRF exposes cloud metadata

Data Extraction Auth Bypass Framework Agent

langchain CWE-918 2.6K 5 ATLAS

CRITICAL EXPLOIT AVAIL

vLLM: RCE via exposed TCPStore in distributed inference

Code Execution Data Extraction Inference Framework

vllm CWE-502 127 4 ATLAS

CRITICAL EXPLOIT AVAIL

vLLM: RCE via pickle deserialization on ZeroMQ

Code Execution Supply Chain Inference Framework

vllm CWE-502 127 5 ATLAS

CRITICAL EXPLOIT AVAIL

PyTorch: RCE bypasses weights_only=True safe-load guard

Code Execution Supply Chain Framework Model Inference

pytorch CWE-502 21.9K 6 ATLAS

CRITICAL EXPLOIT AVAIL

BentoML: RCE via insecure deserialization in runner

Code Execution Data Extraction Supply Chain Framework Inference

bentoml CWE-502 23 5 ATLAS

CRITICAL KEV SCANNER

Langflow: Unauth RCE via code injection endpoint

Code Execution Auth Bypass Framework Agent

langflow CWE-94 5 ATLAS

CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via insecure deserialization

Code Execution Supply Chain Framework Inference

bentoml CWE-502 23 5 ATLAS

CRITICAL EXPLOIT AVAIL

InvokeAI: RCE via unsafe torch.load deserialization

Code Execution Supply Chain Framework Model

CWE-502 5 ATLAS

CRITICAL

vLLM: RCE via pickle deserialization in distributed API

Code Execution Supply Chain Framework Inference

vllm CWE-502 127 3 ATLAS

CRITICAL EXPLOIT AVAIL

llama-index finchat: SQL injection enables RCE

Code Execution Supply Chain Data Extraction Agent Framework Plugin

llama-index-packs-finchat CWE-89 229 5 ATLAS

CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via runner deserialization

Code Execution Supply Chain Framework Inference

bentoml CWE-502 23 3 ATLAS

CRITICAL EXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in RPC server

Code Execution Supply Chain Framework Inference

vllm CWE-78 127 5 ATLAS

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

AI Security Threat Feed

Weekly CISO Take + top threats

Latest AI Security Threats

Need deeper analysis?