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
3,631

AI/ML CVEs Tracked

484

Critical

94

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 2358 results — no patch
CRITICAL

ray: security flaw enables exploitation

CVE-2025-34351
--
EPSS 0.5%
Auth Bypass Code Execution Model Poisoning Framework Training Data Inference
ray CWE-304 635 8 ATLAS
HIGH EXPLOIT AVAIL

mlx: security flaw enables exploitation

CVE-2025-62609
7.5
EPSS 0.4%
DoS Supply Chain Framework Model
mlx CWE-476 391 5 ATLAS
CRITICAL EXPLOIT AVAIL

mlx: security flaw enables exploitation

CVE-2025-62608
9.1
EPSS 0.5%
Supply Chain Code Execution Data Extraction Framework Training Data
mlx CWE-122 391 6 ATLAS
HIGH EXPLOIT AVAIL

AI component: Arbitrary File Upload enables RCE

CVE-2025-12973
7.2
EPSS 0.9%
Code Execution Supply Chain Data Extraction Plugin API
6 ATLAS 1 incident
MEDIUM

vllm: Resource Exhaustion enables DoS

CVE-2025-62426
6.5
EPSS 0.4%
DoS Inference API Framework
vllm CWE-770 92 4 ATLAS
MEDIUM

vllm: security flaw enables exploitation

CVE-2025-62372
6.5
EPSS 0.4%
DoS Inference Framework
vllm CWE-129 92 5 ATLAS
HIGH

vllm: Input Validation flaw enables exploitation

CVE-2025-62164
8.8
EPSS 0.9%
Code Execution DoS Supply Chain Inference API Framework
vllm CWE-20 92 5 ATLAS
LOW EXPLOIT AVAIL

pytorch: security flaw enables exploitation

CVE-2025-63396
3.3
EPSS 0.1%
DoS Framework
pytorch 25.2K 3 ATLAS
MEDIUM

AI component: Info Disclosure leaks sensitive data

CVE-2025-12732
4.3
EPSS 0.3%
Data Extraction Auth Bypass Data Leakage API Plugin
5 ATLAS
MEDIUM

AI component: SQL Injection exposes database

CVE-2025-11972
4.9
EPSS 0.3%
Data Extraction Auth Bypass Plugin API
5 ATLAS
MEDIUM

Better: security flaw enables exploitation

CVE-2025-12360
4.3
EPSS 0.2%
Auth Bypass DoS API Plugin
6 ATLAS
MEDIUM EXPLOIT AVAIL

dspy: security flaw enables exploitation

CVE-2025-12695
5.9
EPSS 0.3%
Data Extraction Code Execution Framework Agent
dspy CWE-653 61 5 ATLAS
HIGH

n8n: security flaw enables exploitation

CVE-2025-62726
8.8
EPSS 0.8%
Code Execution Supply Chain Data Extraction Agent Framework Plugin
n8n 6 ATLAS
LOW EXPLOIT AVAIL

pdf2zh: security flaw enables exploitation

CVE-2025-50736
--
EPSS 0.2%
Social Engineering Auth Bypass API Framework
pdf2zh CWE-601 1 4 ATLAS
UNKNOWN

LiteLLM: Info Disclosure leaks sensitive data

CVE-2025-11203
--
EPSS 0.4%
Data Leakage Data Extraction Auth Bypass API Framework Inference
5 ATLAS
CRITICAL EXPLOIT AVAIL

mlflow: Path Traversal enables file access

CVE-2025-11201
9.8
EPSS 27.0%
Code Execution Auth Bypass Framework
mlflow CWE-22 690 6 ATLAS
CRITICAL

mlflow: security flaw enables exploitation

CVE-2025-11200
9.8
EPSS 1.5%
Auth Bypass Data Extraction Supply Chain Framework Model Training Data
mlflow CWE-521 690 6 ATLAS
MEDIUM EXPLOIT AVAIL

smolagents: security flaw enables exploitation

CVE-2025-11844
5.4
EPSS 0.3%
Data Extraction Auth Bypass Agent Framework Plugin
smolagents CWE-643 103 4 ATLAS
MEDIUM EXPLOIT AVAIL

Moodle: IDOR enables unauthorized data access

CVE-2025-60511
4.3
EPSS 0.2%
Auth Bypass Data Leakage Data Extraction Plugin API
5 ATLAS
CRITICAL EXPLOIT AVAIL

VestaCP: backdoored installer, not an AI/ML CVE

CVE-2018-25117
--
EPSS 0.4%
Supply Chain Code Execution DoS Framework
Control Panel (CP) 505

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