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
3,645

AI/ML CVEs Tracked

487

Critical

91

New This Week

25

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 2369 results — no patch
HIGH EXPLOIT AVAIL

open-webui: unauthenticated DoS disables Admin panel

CVE-2024-7036
7.5
EPSS 0.8%
DoS Framework API
open-webui CWE-400 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: Stored XSS via file upload, session hijack

CVE-2024-7044
6.8
EPSS 0.5%
Auth Bypass Data Extraction Social Engineering Framework API
open-webui CWE-79 3 5 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: auth bypass exposes all user files

CVE-2024-7043
8.1
EPSS 0.6%
Auth Bypass Data Extraction Data Leakage API Framework
open-webui CWE-821 3 4 ATLAS
HIGH

open-webui: DoS via starlette memory exhaustion

GHSA-w466-2wfc-8g58
7.5
DoS Supply Chain Framework API
open-webui CWE-400 3 2 ATLAS
CRITICAL EXPLOIT AVAIL

llama-index finchat: SQL injection enables RCE

CVE-2024-12909
10.0
EPSS 1.4%
Code Execution Supply Chain Data Extraction Agent Framework Plugin
llama-index-packs-finchat CWE-89 249 5 ATLAS
HIGH

BentoML: DoS via multipart boundary in Gradio login

GHSA-hh3j-9m59-p8vc
7.5
DoS Framework Inference
bentoml CWE-400 20 3 ATLAS
MEDIUM

BentoML: open redirect exposes ML teams to phishing

GHSA-564p-rx2q-4c8v
6.1
Social Engineering Auth Bypass Framework Inference
bentoml CWE-601 20 5 ATLAS
HIGH EXPLOIT AVAIL

Open-WebUI: unauthenticated DoS via code formatter

CVE-2024-12537
7.5
EPSS 0.9%
DoS Auth Bypass API Framework
open-webui CWE-400 3 3 ATLAS
HIGH EXPLOIT AVAIL

open-webui: unauthenticated DoS via login payload flood

CVE-2024-12534
7.5
EPSS 0.8%
DoS API Framework
open-webui CWE-400 3 3 ATLAS
HIGH EXPLOIT AVAIL

H2O-3: unauthenticated AST parser enables DoS + file write

CVE-2024-10572
7.5
EPSS 0.7%
DoS Code Execution Framework Training Data
h2o CWE-94 27 3 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: passwordless accounts enable persistent backdoor

CVE-2025-1474
5.5
EPSS 0.4%
Auth Bypass Supply Chain Model Poisoning Framework Training Data Model
mlflow CWE-521 690 5 ATLAS
HIGH EXPLOIT AVAIL

MLflow: CSRF in signup allows rogue account creation

CVE-2025-1473
7.1
EPSS 0.2%
Auth Bypass Data Extraction Framework Training Data
mlflow CWE-352 690 4 ATLAS
HIGH EXPLOIT AVAIL

MLflow: GraphQL DoS disables ML tracking server

CVE-2025-0453
7.5
EPSS 11.0%
DoS Framework
mlflow CWE-400 690 3 ATLAS
HIGH EXPLOIT AVAIL

Ollama: DoS via malicious GGUF model file upload

CVE-2025-0317
7.5
EPSS 14.2%
DoS Inference Model
ollama CWE-369 1.8K 4 ATLAS
HIGH EXPLOIT AVAIL

Ollama: GGUF model upload causes memory exhaustion DoS

CVE-2025-0315
7.5
EPSS 0.7%
DoS Inference Model
ollama CWE-770 1.8K 3 ATLAS
HIGH EXPLOIT AVAIL

Ollama: null pointer DoS via malicious GGUF model upload

CVE-2025-0312
7.5
EPSS 0.6%
DoS Inference Model Framework
ollama CWE-476 1.8K 4 ATLAS
UNKNOWN EXPLOIT AVAIL

Gradio: DoS via oversized upload filename

CVE-2025-0187
--
EPSS 0.7%
DoS Framework API
gradio 721 3 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via runner deserialization

CVE-2024-9070
9.8
EPSS 0.9%
Code Execution Supply Chain Framework Inference
bentoml CWE-502 20 3 ATLAS
HIGH EXPLOIT AVAIL

BentoML: DoS via multipart boundary exhausts server

CVE-2024-9056
7.5
EPSS 0.7%
DoS Framework Inference
bentoml CWE-400 20 3 ATLAS
CRITICAL EXPLOIT AVAIL

vllm: RCE via unsafe pickle deserialization in RPC server

CVE-2024-9053
9.8
EPSS 1.4%
Code Execution Supply Chain Framework Inference
vllm CWE-78 92 5 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