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

96

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 472 results — Medium severity, Active exploitation
MEDIUM EXPLOIT AVAIL

AI component: SQL Injection exposes database

CVE-2025-13922
6.5
EPSS 0.3%
Data Extraction Auth Bypass Plugin API
5 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
MEDIUM EXPLOIT AVAIL

Keras: safe_mode bypass enables file read and SSRF

CVE-2025-12058
--
EPSS 0.2%
Data Extraction Supply Chain Code Execution Framework Model
keras Patch: 3.12.0 CWE-502 1.5K 5 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
MEDIUM EXPLOIT AVAIL

clearml: path traversal in safe_extract → RCE risk

CVE-2025-8917
5.8
EPSS 0.3%
Supply Chain Code Execution Framework Training Data
clearml Patch: 2.0.2 CWE-22 24 4 ATLAS
MEDIUM EXPLOIT AVAIL

TensorFlow: non-deterministic compilation breaks Embedding

CVE-2025-55556
6.5
EPSS 0.2%
Supply Chain DoS Framework Inference
tensorflow 3.8K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: integer overflow in nan_to_num causes DoS

CVE-2025-55554
5.3
EPSS 0.3%
DoS Supply Chain Framework Inference
pytorch 25.2K 3 ATLAS
MEDIUM EXPLOIT AVAIL

Transformers: ReDoS in EnglishNormalizer exhausts CPU

CVE-2025-6051
5.3
EPSS 0.4%
DoS Framework Inference
transformers CWE-1333 9.5K 4 ATLAS
MEDIUM EXPLOIT AVAIL

xgrammar: DoS via oversized JSON schema grammar parsing

CVE-2025-58446
--
EPSS 0.5%
DoS Inference Framework
xgrammar Patch: 0.1.24 CWE-770 126 3 ATLAS
MEDIUM EXPLOIT AVAIL

ExecuTorch: integer overflow enables RCE via model loading

CVE-2025-54952
--
EPSS 0.6%
Code Execution Supply Chain Framework Inference Model
executorch CWE-680 6 4 ATLAS
MEDIUM EXPLOIT AVAIL

Ollama: arbitrary file deletion via /api/pull

CVE-2025-44779
6.6
EPSS 0.2%
DoS Data Leakage Inference Framework
ollama 1.8K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Transformers: ReDoS in TF-to-PyTorch weight converter

CVE-2025-5197
5.3
EPSS 0.4%
DoS Supply Chain Framework
transformers CWE-1333 9.5K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Ollama: auth token hijack via crafted WWW-Authenticate

CVE-2025-51471
6.9
EPSS 15.2%
Auth Bypass Data Extraction Supply Chain Inference API Model
ollama 1.8K 5 ATLAS
MEDIUM EXPLOIT AVAIL

Dagster: path traversal exposes arbitrary file read via gRPC

CVE-2025-51481
6.6
EPSS 0.5%
Data Extraction Data Leakage Framework Training Data
CWE-22 5 ATLAS
MEDIUM EXPLOIT AVAIL

Transformers: ReDoS in DonutProcessor causes DoS

CVE-2025-3933
5.3
EPSS 0.4%
DoS Framework Inference
transformers CWE-1333 9.5K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Contest Gallery WP Plugin: Stored XSS in OpenAI integration

CVE-2025-6716
6.4
EPSS 0.2%
Code Execution Data Leakage Plugin API
4 ATLAS
MEDIUM EXPLOIT AVAIL

OpenAI Operator: fullscreen spoofing captures credentials

CVE-2025-7021
6.5
EPSS 0.3%
Social Engineering Privacy Violation Agent API
operator 14.6K 6 ATLAS
MEDIUM EXPLOIT AVAIL

llama-index: DocugamiReader MD5 hash collision drops chunks

CVE-2025-6211
6.5
EPSS 0.3%
Supply Chain Data Leakage Framework RAG
llama-index-readers-docugami Patch: 0.3.1 CWE-440 249 4 ATLAS
MEDIUM EXPLOIT AVAIL

llama-index Obsidian reader: hardlink path traversal leaks files

CVE-2025-6210
6.2
EPSS 0.3%
Data Extraction Supply Chain Framework RAG
llama-index-readers-obsidian Patch: 0.5.2 CWE-22 249 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