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
3,021

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 859 results — High severity, no patch
HIGH

Merlin Transformers4Rec: code injection via Python dep

CVE-2025-23298
7.8
EPSS 0.7%
Supply Chain Code Execution Framework
4 ATLAS
HIGH EXPLOIT AVAIL

Keras: safe mode bypass enables RCE via model load

CVE-2025-8747
7.8
EPSS 0.1%
Code Execution Supply Chain Framework Model
keras CWE-502 1.6K 5 ATLAS
HIGH

WP Contest Gallery: Stored XSS exposes OpenAI API creds

CVE-2025-7725
7.2
EPSS 0.2%
Data Extraction Code Execution Plugin API
4 ATLAS
HIGH

lollms: timing attack enables credential enumeration

CVE-2025-6386
7.5
EPSS 0.4%
Auth Bypass Data Extraction Framework Agent
lollms CWE-203 4 ATLAS
HIGH EXPLOIT AVAIL

Transformers: ReDoS in chat.py causes CPU exhaustion

CVE-2025-3262
7.5
EPSS 0.4%
DoS Framework
transformers CWE-1333 9.2K 3 ATLAS
HIGH EXPLOIT AVAIL

Langchain-Chatchat: path traversal exposes system files

CVE-2025-6855
8.8
EPSS 0.6%
Data Extraction Code Execution Framework RAG
langchain-chatchat CWE-22 3.0K 5 ATLAS
HIGH EXPLOIT AVAIL

libssh: OOB read in SFTP handle leaks memory

CVE-2025-5318
8.1
EPSS 1.5%
Supply Chain Data Leakage DoS Inference
rhaiis/vllm-cuda-rhel9 130 1 ATLAS
HIGH

Hive Support WP: OpenAI key theft + prompt hijack

CVE-2025-5018
7.1
EPSS 0.3%
Auth Bypass Data Extraction Prompt Injection API Plugin
6 ATLAS
HIGH EXPLOIT AVAIL

Gradio: unauthenticated file copy enables disk DoS

CVE-2025-48889
7.5
EPSS 0.6%
DoS Framework Inference
gradio CWE-434 673 3 ATLAS
HIGH

vLLM: image hash collision enables multimodal cache leakage

CVE-2025-46722
7.3
EPSS 0.3%
Data Leakage Privacy Violation Inference Framework
vllm CWE-1023 130 4 ATLAS
HIGH EXPLOIT AVAIL

llama-index-cli: OS command injection enables RCE

CVE-2025-1753
7.8
EPSS 1.0%
Code Execution Supply Chain Framework Agent
llama-index CWE-78 245 4 ATLAS
HIGH

label-studio-ml: PyTorch .pt deserialization RCE in YOLO loader

CVE-2025-5173
7.8
EPSS 0.2%
Supply Chain Code Execution Framework Model
label-studio-ml CWE-502 2 4 ATLAS
HIGH EXPLOIT AVAIL

transformers: ReDoS in testing_utils causes DoS

CVE-2025-2099
7.5
EPSS 0.5%
DoS Framework
transformers CWE-1333 9.2K 3 ATLAS
HIGH

TensorFlow Serving: JSON recursion DoS on inference API

CVE-2025-0649
7.5
EPSS 0.2%
DoS Inference API Framework
tensorflow_serving CWE-787 3.7K 3 ATLAS
HIGH

vLLM: pickle RCE in multi-node inference deployments

CVE-2025-30165
8.0
EPSS 0.5%
Code Execution Inference Framework
vllm CWE-502 130 3 ATLAS
HIGH EXPLOIT AVAIL

vLLM: DoS via quadratic multimodal tokenizer input

CVE-2025-46560
7.5
EPSS 0.5%
DoS Inference Framework
vllm CWE-1333 130 3 ATLAS
HIGH EXPLOIT AVAIL

vLLM: ZeroMQ socket exposure enables DoS in multi-node

CVE-2025-30202
7.5
EPSS 0.6%
DoS Data Leakage Inference Framework
vllm CWE-770 130 4 ATLAS
HIGH

Mesop: class pollution enables DoS and LLM jailbreak

CVE-2025-30358
8.1
EPSS 0.6%
Jailbreak DoS Auth Bypass Framework Agent
CWE-915 6 ATLAS
HIGH EXPLOIT AVAIL

LiteLLM: Langfuse API key leak via error handling

CVE-2025-0330
7.5
EPSS 0.5%
Data Leakage Auth Bypass Data Extraction Framework API Inference
litellm CWE-1230 6 4 ATLAS
HIGH

open-webui: DoS via unauthenticated multipart parsing

GHSA-5ccf-884p-4jjq
7.5
DoS Inference RAG Framework
open-webui CWE-400 4 3 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