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
3,018

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 1076 results — has patch
HIGH

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-67644
7.3
EPSS 2.3%
Auth Bypass Data Extraction Framework Agent
langgraph-checkpoint-sqlite Patch: 3.0.1 CWE-89 3.7K 4 ATLAS
HIGH EXPLOIT AVAIL

open-webui: SSRF allows internal network access

CVE-2025-65958
8.5
EPSS 4.5%
Data Extraction Data Leakage Code Execution API RAG
open-webui Patch: 0.6.37 CWE-918 4 6 ATLAS
CRITICAL KEV

ray: Code Injection enables RCE

CVE-2025-62593
--
EPSS 0.4%
Code Execution Auth Bypass Social Engineering Framework
ray Patch: 2.52.0 CWE-94 619 8 ATLAS
HIGH

langchain-core: security flaw enables exploitation

CVE-2025-65106
--
EPSS 0.5%
Prompt Injection Code Execution Data Extraction Framework Agent
langchain-core Patch: 1.0.7 CWE-1336 5.5K 7 ATLAS
HIGH EXPLOIT AVAIL

open-webui: Code Injection enables RCE

CVE-2025-64496
7.3
EPSS 7.8%
Code Execution Auth Bypass Social Engineering Inference API Plugin
open-webui Patch: 0.6.35 CWE-95 4 9 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: XSS-to-RCE via malicious prompt injection

CVE-2025-64495
8.7
EPSS 0.5%
Code Execution Data Extraction Auth Bypass Framework Agent API
open-webui Patch: 0.6.35 CWE-79 4 7 ATLAS
HIGH EXPLOIT AVAIL

langgraph-checkpoint: Deserialization enables RCE

CVE-2025-64439
--
EPSS 0.9%
Code Execution Supply Chain Framework Agent
langgraph-checkpoint Patch: 3.0.0 CWE-502 3.7K 5 ATLAS
CRITICAL EXPLOIT AVAIL

keras: Path Traversal enables file access

CVE-2025-12060
9.8
EPSS 0.6%
Supply Chain Code Execution Framework Training Data
keras Patch: 3.12.0 CWE-22 1.5K 4 ATLAS
HIGH EXPLOIT AVAIL

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-64104
7.3
EPSS 0.2%
Auth Bypass Data Extraction Data Leakage Framework Agent
langgraph-checkpoint-sqlite Patch: 2.0.11 CWE-89 3.7K 4 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
HIGH EXPLOIT AVAIL

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-8709
7.3
EPSS 0.2%
Data Extraction Auth Bypass Data Leakage Framework Agent
langgraph-checkpoint-sqlite Patch: 2.0.11 CWE-89 3.7K 5 ATLAS
CRITICAL EXPLOIT AVAIL

keras: Deserialization enables RCE

CVE-2025-49655
9.8
EPSS 0.7%
Code Execution Supply Chain Framework Model
keras Patch: 3.11.3 CWE-502 1.5K 5 ATLAS
HIGH

llama-index: world-writable NLTK dir allows local tampering

CVE-2025-7707
7.1
EPSS 0.2%
DoS Supply Chain Model Poisoning Framework RAG
llama-index Patch: 0.13.0 CWE-377 244 4 ATLAS
MEDIUM

vllm: DoS via Jinja template injection in chat API

CVE-2025-61620
6.5
EPSS 0.2%
DoS Framework Inference API
vllm Patch: 0.11.0 CWE-20 130 5 ATLAS
HIGH EXPLOIT AVAIL

vLLM: SSRF in media loader exposes internal network

CVE-2025-6242
7.1
EPSS 0.2%
Data Extraction Auth Bypass Inference Framework
vllm Patch: 0.11.0 CWE-601 130 4 ATLAS
HIGH EXPLOIT AVAIL

LLaMA-Factory: SSRF+LFI in multimodal chat API

CVE-2025-61784
8.1
EPSS 0.4%
Data Extraction Privacy Violation Code Execution Framework API Training Data
llamafactory Patch: 0.9.4 CWE-918 2 6 ATLAS
HIGH EXPLOIT AVAIL

langchain-text-splitters: XXE enables arbitrary file read

CVE-2025-6985
7.5
EPSS 0.6%
Data Extraction Supply Chain Data Leakage Framework RAG Agent
langchain-text-splitters Patch: 0.3.9 CWE-611 3.0K 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 25 4 ATLAS
HIGH EXPLOIT AVAIL

llama-index-core: insecure /tmp dir, model theft risk

CVE-2025-7647
7.3
EPSS 0.1%
Data Extraction Model Poisoning Supply Chain Framework RAG
llama-index-core Patch: 0.13.0 CWE-378 1.2K 5 ATLAS
LOW

JupyterLab: missing noopener enables reverse tabnabbing

CVE-2025-59842
--
EPSS 0.2%
Social Engineering Supply Chain Framework
jupyterlab Patch: 4.4.8 CWE-1022 1.9K 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