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
3,591

AI/ML CVEs Tracked

481

Critical

84

New This Week

24

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 2346 results — no patch
HIGH

Gradio: CORS bypass exposes local instances to credential theft

CVE-2024-47084
8.3
EPSS 0.5%
Auth Bypass Data Extraction Data Leakage Framework Inference
gradio CWE-285 721 5 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: IDOR enables cross-user memory tampering

CVE-2024-7041
6.5
EPSS 0.4%
Auth Bypass Model Poisoning Privacy Violation API Agent Framework
open-webui CWE-250 3 4 ATLAS
LOW EXPLOIT AVAIL

open-webui: filesystem enumeration via admin error messages

CVE-2024-7038
2.7
EPSS 0.3%
Data Extraction Data Leakage Framework Inference RAG
open-webui CWE-200 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

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

CVE-2024-7037
6.5
EPSS 1.1%
Code Execution Supply Chain Framework Plugin
open-webui CWE-22 3 4 ATLAS
MEDIUM EXPLOIT AVAIL

Langflow: ReDoS crashes LLM workflow backend via HTTP POST

CVE-2024-9277
6.5
EPSS 1.0%
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 0.8%
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 1.1%
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 1.4%
Code Execution Supply Chain Framework Agent
langchain-experimental 3.0K 4 ATLAS
CRITICAL

Panel: file exposure enables sensitive ML data collection

CVE-2024-6878
--
EPSS 0.4%
Data Extraction Privacy Violation Framework Inference
Panel 505 4 ATLAS
CRITICAL

Panel: Reflected XSS enables session hijack in ML UI

CVE-2024-6877
--
EPSS 0.3%
Code Execution Data Leakage Auth Bypass Framework API
Panel 505 4 ATLAS
CRITICAL

Panel: plaintext credential storage enables domain compromise

CVE-2024-5960
9.8
EPSS 0.4%
Auth Bypass Data Extraction Privacy Violation Framework Inference
Panel 505 3 ATLAS
CRITICAL

Panel: Stored XSS enables session hijack in ML dashboards

CVE-2024-5959
--
EPSS 0.3%
Auth Bypass Data Extraction Code Execution Framework API
Panel 505 3 ATLAS
CRITICAL

Panel: SQL injection enables OS command execution

CVE-2024-5958
--
EPSS 0.5%
Code Execution Data Extraction Auth Bypass Framework Inference
Panel 505 4 ATLAS
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
HIGH EXPLOIT AVAIL

vLLM: unauthenticated DoS via empty completion prompt

CVE-2024-8768
7.5
EPSS 0.7%
DoS Inference API Framework
4 ATLAS
HIGH EXPLOIT AVAIL

LangChain: RCE via FAISS pickle deserialization

CVE-2024-5998
7.8
EPSS 0.4%
Code Execution Supply Chain Framework RAG
langchain 3.0K 4 ATLAS
HIGH KEV

LiteLLM: SSRF leaks OpenAI API key to attacker

CVE-2024-6587
7.5
EPSS 35.3%
Data Extraction Auth Bypass API Framework
litellm 6 5 ATLAS
HIGH EXPLOIT AVAIL

MindsDB: RCE via eval() injection in ChromaDB INSERT

CVE-2024-45848
8.8
EPSS 0.9%
Code Execution Data Extraction Framework RAG Plugin
CWE-94 5 ATLAS
HIGH EXPLOIT AVAIL

Ollama: ZIP path traversal exposes host filesystem

CVE-2024-45436
7.5
EPSS 2.6%
Supply Chain Data Extraction Framework Model Inference
ollama CWE-22 1.8K 6 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

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