AI Threat Alert AI Threat Alert

AI Security Threat Feed

Latest CVEs affecting AI/ML systems, updated continuously. Tracked from NVD, GitHub Advisory, and CISA KEV.

1,604

AI/ML CVEs Tracked

225

Critical

79

New This Week

16

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 144 results — Active exploitation, has patch
HIGH EXPLOIT AVAIL

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

CVE-2025-64495
8.7
EPSS 0.0%
Code Execution Data Extraction Auth Bypass Framework Agent API
open-webui Patch: 0.6.35 CWE-79 7 ATLAS
HIGH EXPLOIT AVAIL

langgraph-checkpoint: Deserialization enables RCE

CVE-2025-64439
--
EPSS 1.1%
Code Execution Supply Chain Framework Agent
langgraph-checkpoint Patch: 3.0.0 CWE-502 3.1K 5 ATLAS
CRITICAL EXPLOIT AVAIL

keras: Path Traversal enables file access

CVE-2025-12060
9.8
EPSS 0.1%
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 0.0%
Auth Bypass Data Extraction Data Leakage Framework Agent
langgraph-checkpoint-sqlite Patch: 2.0.11 CWE-89 3.1K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Keras: safe_mode bypass enables file read and SSRF

CVE-2025-12058
--
EPSS 0.1%
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 0.0%
Data Extraction Auth Bypass Data Leakage Framework Agent
langgraph-checkpoint-sqlite Patch: 2.0.11 CWE-89 3.1K 5 ATLAS
CRITICAL EXPLOIT AVAIL

keras: Deserialization enables RCE

CVE-2025-49655
9.8
EPSS 0.1%
Code Execution Supply Chain Framework Model
keras Patch: 3.11.3 CWE-502 1.5K 5 ATLAS
HIGH EXPLOIT AVAIL

vLLM: SSRF in media loader exposes internal network

CVE-2025-6242
7.1
EPSS 0.1%
Data Extraction Auth Bypass Inference Framework
vllm Patch: 0.11.0 CWE-601 126 4 ATLAS
HIGH EXPLOIT AVAIL

LLaMA-Factory: SSRF+LFI in multimodal chat API

CVE-2025-61784
8.1
EPSS 0.1%
Data Extraction Privacy Violation Code Execution Framework API Training Data
llamafactory Patch: 0.9.4 CWE-918 1 6 ATLAS
HIGH EXPLOIT AVAIL

langchain-text-splitters: XXE enables arbitrary file read

CVE-2025-6985
7.5
EPSS 0.2%
Data Extraction Supply Chain Data Leakage Framework RAG Agent
langchain-text-splitters Patch: 0.3.9 CWE-611 2.6K 5 ATLAS
MEDIUM EXPLOIT AVAIL

clearml: path traversal in safe_extract → RCE risk

CVE-2025-8917
5.8
EPSS 0.0%
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 0.0%
Data Extraction Model Poisoning Supply Chain Framework RAG
llama-index-core Patch: 0.13.0 CWE-378 1.1K 5 ATLAS
HIGH EXPLOIT AVAIL

Picklescan: CRC bypass hides malicious pickle in ZIP

CVE-2025-10156
7.5
EPSS 1.0%
Supply Chain Code Execution Model Framework
picklescan Patch: 0.0.31 CWE-693 3 5 ATLAS 1 incident
HIGH EXPLOIT AVAIL

PickleScan: subclass bypass enables malicious model RCE

CVE-2025-10157
8.3
EPSS 0.2%
Supply Chain Code Execution Model Framework
picklescan Patch: 0.0.31 CWE-693 3 5 ATLAS 1 incident
HIGH EXPLOIT AVAIL

MONAI: unsafe pickle deserialization RCE in data pipeline

CVE-2025-58757
8.8
EPSS 0.8%
Code Execution Supply Chain Framework Training Data
monai Patch: 1.5.1 CWE-502 105 5 ATLAS
HIGH EXPLOIT AVAIL

MONAI: unsafe deserialization in CheckpointLoader allows RCE

CVE-2025-58756
8.8
EPSS 1.7%
Code Execution Supply Chain Framework Training Data
monai Patch: 1.5.1 CWE-502 105 5 ATLAS
HIGH EXPLOIT AVAIL

MONAI: path traversal allows arbitrary file write

CVE-2025-58755
8.8
EPSS 0.1%
Supply Chain Code Execution Framework
monai Patch: 1.5.1 CWE-22 105 4 ATLAS
MEDIUM EXPLOIT AVAIL

xgrammar: DoS via oversized JSON schema grammar parsing

CVE-2025-58446
--
EPSS 0.1%
DoS Inference Framework
xgrammar Patch: 0.1.24 CWE-770 152 3 ATLAS
HIGH EXPLOIT AVAIL SCANNER

EverNoteLoader: XXE exposes host files in LangChain

CVE-2025-6984
7.5
EPSS 1.9%
Data Extraction Data Leakage Framework RAG
langchain-community Patch: 0.3.27 CWE-200 1.2K 4 ATLAS
HIGH EXPLOIT AVAIL

llama-index: JSON parsing DoS via deep recursion

CVE-2025-5302
8.6
EPSS 0.1%
DoS Framework RAG
llama-index-core Patch: 0.12.38 CWE-674 1.1K 3 ATLAS

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