AI Threat Alert AI Threat Alert

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

77

New This Week

16

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 910 results — Active exploitation
HIGH EXPLOIT AVAIL

Ollama: OOB read in GGUF parser enables remote DoS

CVE-2024-39720
8.2
EPSS 0.3%
DoS Code Execution Inference Framework
ollama 1.5K 3 ATLAS
HIGH EXPLOIT AVAIL

Ollama: file existence oracle via api/create errors

CVE-2024-39719
7.5
EPSS 44.5%
Data Extraction Privacy Violation Inference API
ollama 1.5K 4 ATLAS
CRITICAL EXPLOIT AVAIL

Langflow: Unauthenticated RCE via PythonCodeTool

CVE-2024-42835
9.8
EPSS 14.3%
Code Execution Supply Chain Data Extraction Framework Agent Plugin
langflow 6 ATLAS
CRITICAL EXPLOIT AVAIL

PyTorch: RCE via RemoteModule deserialization

CVE-2024-48063
9.8
EPSS 25.1%
Code Execution Supply Chain Framework Training Data
pytorch CWE-502 21.9K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Lollms: SVG upload XSS enables session hijack and RCE

CVE-2024-6581
6.5
EPSS 1.6%
Code Execution Data Leakage Social Engineering Framework API
lollms CWE-79 4 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain GraphCypher: prompt injection enables DB wipe

CVE-2024-8309
9.8
EPSS 2.0%
Prompt Injection Data Extraction DoS Framework Agent RAG
langchain CWE-74 2.6K 7 ATLAS
CRITICAL EXPLOIT AVAIL

LangChain.js: path traversal, arbitrary file read/write

CVE-2024-7774
9.1
EPSS 0.6%
Data Extraction Code Execution Data Leakage Framework Agent
langchain.js CWE-22 2.6K 5 ATLAS
CRITICAL EXPLOIT AVAIL

LangChainJS: prompt injection enables full graph DB takeover

CVE-2024-7042
9.8
EPSS 0.1%
Prompt Injection Data Extraction Code Execution Framework Agent API
langchain 2.6K 6 ATLAS
CRITICAL EXPLOIT AVAIL

Affiliator WP Plugin: Unauthenticated Web Shell Upload

CVE-2024-49326
9.8
EPSS 0.6%
Code Execution Auth Bypass Supply Chain Framework API
affiliator 1.5K 6 ATLAS
MEDIUM EXPLOIT AVAIL

lollms: path traversal allows arbitrary directory read

CVE-2024-6985
4.4
EPSS 0.1%
Data Extraction Auth Bypass Framework Agent
lollms CWE-23 4 ATLAS
LOW EXPLOIT AVAIL

lollms: path traversal in RAG database functions

CVE-2024-6971
3.4
EPSS 0.0%
Data Extraction Code Execution RAG Framework Agent
lollms CWE-22 4 ATLAS
HIGH EXPLOIT AVAIL

Gradio: path traversal leaks arbitrary server files

CVE-2024-47868
7.5
EPSS 0.2%
Data Extraction Data Leakage Framework Inference
gradio CWE-22 679 5 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: IDOR enables cross-user memory tampering

CVE-2024-7041
6.5
EPSS 0.1%
Auth Bypass Model Poisoning Privacy Violation API Agent Framework
open-webui CWE-250 4 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: path traversal → arbitrary file write/RCE

CVE-2024-7037
6.5
EPSS 2.3%
Code Execution Supply Chain Framework Plugin
open-webui CWE-22 4 ATLAS
LOW EXPLOIT AVAIL

open-webui: filesystem enumeration via admin error messages

CVE-2024-7038
2.7
EPSS 0.2%
Data Extraction Data Leakage Framework Inference RAG
open-webui CWE-200 3 ATLAS
MEDIUM EXPLOIT AVAIL

Langflow: ReDoS crashes LLM workflow backend via HTTP POST

CVE-2024-9277
6.5
EPSS 0.2%
DoS Framework
langflow CWE-1333 3 ATLAS
HIGH EXPLOIT AVAIL SCANNER

AYS ChatGPT WP Plugin: auth bypass disables AI service

CVE-2024-7714
7.5
EPSS 23.9%
Auth Bypass Data Leakage DoS Plugin API
4 ATLAS 1 incident
MEDIUM EXPLOIT AVAIL SCANNER

ChatGPT WP Plugin: OpenAI API key leak via unauth REST

CVE-2024-6845
5.3
EPSS 21.6%
Data Extraction Auth Bypass API Plugin
CWE-862 5 ATLAS 1 incident
CRITICAL EXPLOIT AVAIL

LangChain-Experimental: RCE via eval in math chain

CVE-2024-46946
9.8
EPSS 0.7%
Code Execution Supply Chain Framework Agent
langchain-experimental 2.6K 4 ATLAS
MEDIUM EXPLOIT AVAIL

ilab/vllm: best_of param causes inference API DoS

CVE-2024-8939
6.2
EPSS 0.0%
DoS Inference API
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