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 1092 results — no patch

UNKNOWN EXPLOIT AVAIL

lollms-webui: RCE via malicious GGUF model loading

CVE-2024-4897

EPSS 0.8%

1y ago

Supply Chain Code Execution Framework Model Inference

6 ATLAS

CRITICAL EXPLOIT AVAIL

Gradio: code injection via component metadata (CVSS 9.8)

Code Execution Supply Chain Framework Inference

gradio 679 4 ATLAS

MEDIUM EXPLOIT AVAIL

Flowise: reflected XSS enables credential theft

Data Extraction Auth Bypass Social Engineering Agent Framework

flowise CWE-79 5 ATLAS

MEDIUM EXPLOIT AVAIL

Flowise: reflected XSS enables file read chain via chatflow

Code Execution Data Extraction Privacy Violation Agent Framework

flowise CWE-79 5 ATLAS

MEDIUM EXPLOIT AVAIL

Flowise: reflected XSS in chatflow API enables session hijack

Data Extraction Auth Bypass Code Execution Framework Agent

flowise CWE-79 5 ATLAS

MEDIUM EXPLOIT AVAIL

Flowise: reflected XSS enables session hijack and file read

Data Leakage Data Extraction Framework Agent

flowise CWE-79 4 ATLAS

HIGH EXPLOIT AVAIL

Flowise: CORS wildcard enables file read and data theft

Data Extraction Auth Bypass Data Leakage Agent Framework

flowise CWE-346 5 ATLAS

HIGH EXPLOIT AVAIL

Flowise: unauthenticated arbitrary file read via API

Data Extraction Auth Bypass Data Leakage Framework API Agent

flowise CWE-74 6 ATLAS

LOW EXPLOIT AVAIL

lollms-webui: CSRF allows unauthorized AI service install

Supply Chain Auth Bypass Inference Framework

lollms-webui 4 ATLAS

MEDIUM EXPLOIT AVAIL SCANNER

Gradio: open redirect enables phishing against ML users

Social Engineering Privacy Violation Framework Inference

gradio 679 5 ATLAS

HIGH EXPLOIT AVAIL

LangChain: Python REPL code execution without opt-in

Code Execution Prompt Injection Data Extraction Framework Agent

langchain-experimental 2.6K 5 ATLAS

CRITICAL EXPLOIT AVAIL

Langflow: unauthenticated RCE via custom component API

Code Execution Auth Bypass Supply Chain Framework Agent API

langflow CWE-94 5 ATLAS

MEDIUM EXPLOIT AVAIL

scikit-learn: TfidfVectorizer leaks training data tokens

Data Leakage Data Extraction Privacy Violation Framework Training Data

scikit-learn CWE-922 28.2K 5 ATLAS

HIGH EXPLOIT AVAIL

litellm: arbitrary file deletion via audio endpoint

Auth Bypass DoS Framework API

litellm 4 3 ATLAS

CRITICAL EXPLOIT AVAIL SCANNER

ChuanhuChatGPT: path traversal exposes LLM API keys

Data Extraction Auth Bypass Data Leakage Framework API

chuanhuchatgpt 5 ATLAS

MEDIUM EXPLOIT AVAIL

MLflow: URL encoding bypass enables model poisoning

Model Poisoning DoS Framework Model

mlflow 624 5 ATLAS

HIGH EXPLOIT AVAIL

LangChain: SSRF in Web Retriever exposes cloud metadata

Data Extraction Auth Bypass Framework Agent RAG

langchain 2.6K 4 ATLAS

HIGH EXPLOIT AVAIL SCANNER

MLflow: URI fragment LFI exposes arbitrary files

Data Extraction Supply Chain Framework Model Training Data

mlflow CWE-22 624 6 ATLAS

HIGH EXPLOIT AVAIL

MLflow: path traversal enables RCE via dataset loading

Code Execution Supply Chain Data Leakage Framework Training Data

mlflow 624 5 ATLAS

CRITICAL EXPLOIT AVAIL

pytorch-lightning: RCE via deepdiff Delta deserialization

Code Execution Supply Chain Framework

pytorch_lightning CWE-913 21.9K 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?