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
3,018

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 648 results — Medium severity, no patch
MEDIUM EXPLOIT AVAIL SCANNER

ChatGPT WP Plugin: OpenAI API key leak via unauth REST

CVE-2024-6845
5.3
EPSS 1.1%
Data Extraction Auth Bypass API Plugin
CWE-862 5 ATLAS 1 incident
MEDIUM EXPLOIT AVAIL

ilab/vllm: best_of param causes inference API DoS

CVE-2024-8939
6.2
EPSS 0.2%
DoS Inference API
3 ATLAS
MEDIUM EXPLOIT AVAIL

Streamlit: path traversal leaks Windows NTLM hash

CVE-2024-42474
6.5
EPSS 0.6%
Data Leakage Auth Bypass Framework API
streamlit CWE-22 3.0K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: reflected XSS enables credential theft

CVE-2024-37146
6.1
EPSS 0.4%
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

CVE-2024-37145
6.1
EPSS 0.5%
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

CVE-2024-36423
6.1
EPSS 0.4%
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

CVE-2024-36422
6.1
EPSS 0.4%
Data Leakage Data Extraction Framework Agent
flowise CWE-79 4 ATLAS
MEDIUM EXPLOIT AVAIL SCANNER

Gradio: open redirect enables phishing against ML users

CVE-2024-4940
6.1
EPSS 1.0%
Social Engineering Privacy Violation Framework Inference
gradio 669 5 ATLAS
MEDIUM EXPLOIT AVAIL

scikit-learn: TfidfVectorizer leaks training data tokens

CVE-2024-5206
4.7
EPSS 0.2%
Data Leakage Data Extraction Privacy Violation Framework Training Data
scikit-learn CWE-922 30.6K 5 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: URL encoding bypass enables model poisoning

CVE-2024-3099
5.4
EPSS 0.4%
Model Poisoning DoS Framework Model
mlflow 674 5 ATLAS
MEDIUM EXPLOIT AVAIL

WP Testimonial Carousel: OpenAI API key hijack, no auth

CVE-2024-4858
5.3
EPSS 0.4%
Auth Bypass DoS API Plugin
CWE-862 4 ATLAS
MEDIUM EXPLOIT AVAIL

wpbot: missing auth exposes OpenAI account files

CVE-2024-0451
5.0
EPSS 0.4%
Data Extraction Auth Bypass API Plugin
wpbot CWE-862 5 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: broken access control allows artifact deletion

CVE-2024-4263
5.4
EPSS 0.3%
Auth Bypass Framework Training Data
mlflow 674 3 ATLAS
MEDIUM

A flaw was discovered in the RESTEasy Reactive implementation in Quarkus. Due to security checks for some JAX-RS endpoints being performed after serialization,...

CVE-2024-1726
5.3
EPSS 0.7%
MEDIUM

PyTorch: OOB read in mobile model loader leaks memory

CVE-2024-31584
5.5
EPSS 0.4%
Supply Chain Data Extraction Framework Model
pytorch 24.2K 5 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: heap buffer overflow causes local DoS

CVE-2024-31580
4.0
EPSS 0.2%
DoS Framework
pytorch 24.2K 3 ATLAS
MEDIUM

stable-diffusion-webui: path traversal file write

CVE-2024-31462
6.3
EPSS 0.7%
Code Execution Framework Inference
3 ATLAS
MEDIUM EXPLOIT AVAIL

Ollama: DNS rebinding exposes LLM API to remote access

CVE-2024-28224
6.6
EPSS 0.3%
Auth Bypass DoS Data Extraction Inference API Model
ollama 1.7K 4 ATLAS
MEDIUM

A vulnerability in the Eclipse Vert.x toolkit results in a memory leak due to using Netty FastThreadLocal data structures. Specifically, when the Vert.x HTTP...

CVE-2024-1023
6.5
EPSS 1.7%
MEDIUM EXPLOIT AVAIL

Gradio: SSRF exposes internal HuggingFace endpoints

CVE-2024-2206
6.5
EPSS 0.4%
Data Extraction Auth Bypass Framework Inference API
gradio 669 4 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