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 1604 results

CRITICAL EXPLOIT AVAIL SCANNER

MLflow: unauth file overwrite enables model poisoning

Code Execution Model Poisoning Supply Chain Framework Model Training Data

mlflow 624 5 ATLAS

HIGH EXPLOIT AVAIL

MLflow: unauthenticated arbitrary file write via PUT

Supply Chain Code Execution Model Poisoning Framework Model Training Data

mlflow 624 6 ATLAS

CRITICAL EXPLOIT AVAIL

MLeap: zip slip in model loading enables RCE

Supply Chain Code Execution Framework Model

3 ATLAS

HIGH

Infinite Image Browsing: path traversal leaks credentials

Data Extraction Auth Bypass Privacy Violation Framework Inference

5 ATLAS

CRITICAL

LangChain: prompt injection → SQL RCE (CVSS 9.8)

CVE-2023-32785

9.8

2y ago

Prompt Injection Code Execution Data Extraction Framework Agent

langchain Patch: 0.0.247 CWE-74 2.6K 5 ATLAS

HIGH EXPLOIT AVAIL

LangChain: prompt injection triggers SSRF via URL fetch

Prompt Injection Data Extraction Framework Agent

langchain CWE-74 2.6K 5 ATLAS

HIGH KEV

LangChain: SSRF in URL loader exposes internal network

Data Extraction Auth Bypass Framework RAG

langchain CWE-918 2.6K 4 ATLAS

CRITICAL KEV

LangChain: RCE bypass via __import__ in PAL chain

Code Execution Auth Bypass Framework Agent

langchain_experimental 2.6K 4 ATLAS

CRITICAL KEV SCANNER

TorchServe: SSRF + RCE via unrestricted model URL loading

Code Execution Supply Chain Data Extraction Framework Inference Model

torchserve 21.9K 5 ATLAS

MEDIUM

Gradio: arbitrary file upload via /upload endpoint

Code Execution Data Extraction Supply Chain Framework Inference

gradio CWE-434 679 4 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain: RCE via numexpr evaluate injection

Code Execution Supply Chain Framework Agent Plugin

langchain CWE-94 2.6K 5 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain: RCE via malicious JSON prompt template

Code Execution Supply Chain Framework Agent

langchain CWE-94 2.6K 4 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain: RCE via unsanitized PythonAstREPL input

Code Execution Prompt Injection Framework Agent Plugin

langchain CWE-74 2.6K 5 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain: RCE via unsandboxed LLM code execution

Code Execution Prompt Injection Data Extraction Framework Agent API

langchain CWE-74 2.6K 5 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain: RCE via unsanitized prompt parameter

Code Execution Prompt Injection Data Extraction Framework Agent

langchain CWE-94 2.6K 7 ATLAS

HIGH

Intel TF Opt: buffer overflow enables local priv-esc

Code Execution Supply Chain Framework Training Data

optimization_for_tensorflow CWE-119 3.7K 3 ATLAS

CRITICAL EXPLOIT AVAIL

LangChain PALChain: RCE via unsanitized exec() calls

Code Execution Prompt Injection Framework Agent

langchain CWE-94 2.6K 5 ATLAS

HIGH EXPLOIT AVAIL

MLflow: OS command injection enables local code execution

Code Execution Supply Chain Framework Training Data Model

mlflow CWE-78 624 5 ATLAS

CRITICAL EXPLOIT AVAIL SCANNER

MLflow: path traversal allows arbitrary file read

Data Extraction Data Leakage Supply Chain Framework Model Training Data

mlflow 624 6 ATLAS

CRITICAL EXPLOIT AVAIL

QuickAI: unauthenticated SQLi exposes OpenAI API keys

Data Extraction Auth Bypass API

quickai_openai 13.8K 3 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?