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 435 results — High severity, Active exploitation
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
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
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

vLLM: timing attack enables API key bypass

CVE-2025-59425
7.5
EPSS 0.4%
Auth Bypass Inference API
vllm CWE-385 126 5 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
HIGH EXPLOIT AVAIL

Flowise: unrestricted file upload enables persistent RCE

CVE-2025-61687
8.8
EPSS 0.3%
Code Execution Data Leakage Supply Chain Agent Framework
flowise 6 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

PyTorch: DoS via sparse/dense tensor Inductor compile

CVE-2025-55560
7.5
EPSS 0.1%
DoS Framework Inference
pytorch 21.7K 4 ATLAS
HIGH EXPLOIT AVAIL

TensorFlow: DoS via Conv2D valid padding crash

CVE-2025-55559
7.5
EPSS 0.1%
DoS Framework Inference
tensorflow 3.7K 3 ATLAS
HIGH EXPLOIT AVAIL

PyTorch: Inductor compiler buffer overflow causes DoS

CVE-2025-55558
7.5
EPSS 0.1%
DoS Framework Inference
pytorch 21.7K 4 ATLAS
HIGH EXPLOIT AVAIL

PyTorch: DoS via cummin+Inductor NameError in 2.7.0

CVE-2025-55557
7.5
EPSS 0.1%
DoS Framework
pytorch 21.7K 3 ATLAS
HIGH EXPLOIT AVAIL

PyTorch 2.7.0: DoS via proxy_tensor.py syntax error

CVE-2025-55553
7.5
EPSS 0.1%
DoS Supply Chain Framework Inference
pytorch 21.7K 3 ATLAS
HIGH EXPLOIT AVAIL

PyTorch: integer overflow in rot90+randn_like causes DoS

CVE-2025-55552
7.5
EPSS 0.1%
DoS Supply Chain Framework Inference
pytorch CWE-190 21.7K 3 ATLAS
HIGH EXPLOIT AVAIL

PyTorch: DoS in linalg.lu via malformed slice op

CVE-2025-55551
7.5
EPSS 0.1%
DoS Framework Inference
pytorch 21.7K 4 ATLAS
HIGH EXPLOIT AVAIL

Transformers: ReDoS in optimizer halts training pipelines

CVE-2025-6921
7.5
EPSS 0.0%
DoS Framework Training Data
transformers CWE-400 7.8K 4 ATLAS
HIGH EXPLOIT AVAIL

Flowise: unauthenticated SSRF exposes internal network

CVE-2025-59527
7.5
EPSS 0.1%
Data Extraction Privacy Violation Agent Framework
flowise 4 ATLAS
HIGH EXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via model load

CVE-2025-9906
7.3
EPSS 0.1%
Code Execution Supply Chain Framework Model
keras CWE-502 1.5K 6 ATLAS
HIGH EXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via .h5 model files

CVE-2025-9905
7.3
EPSS 0.0%
Code Execution Supply Chain Framework Model
keras CWE-913 1.5K 5 ATLAS
HIGH EXPLOIT AVAIL

picklescan: file extension bypass allows model RCE

CVE-2025-10155
7.8
EPSS 0.1%
Supply Chain Code Execution Model Framework
picklescan CWE-20 3 5 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