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
3,021

AI/ML CVEs Tracked

424

Critical

114

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 3021 results
MEDIUM

vLLM: DoS via unbounded XGrammar schema cache

GHSA-hf3c-wxg2-49q9
6.5
DoS Supply Chain Inference Framework API
vllm Patch: 0.8.4 CWE-770 130 5 ATLAS
CRITICAL EXPLOIT AVAIL

jupyter-remote-desktop-proxy: VNC network exposure

CVE-2025-32428
--
EPSS 0.9%
Auth Bypass Data Leakage Privacy Violation Framework
jupyter-remote-desktop-proxy Patch: 3.0.1 CWE-668 1.9K 5 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: RCE via insecure deserialization in runner

CVE-2025-32375
9.8
EPSS 50.4%
Code Execution Data Extraction Supply Chain Framework Inference
bentoml CWE-502 20 5 ATLAS
MEDIUM

xgrammar: unbounded grammar cache causes LLM server DoS

CVE-2025-32381
6.5
EPSS 0.5%
DoS Inference Framework
xgrammar Patch: 0.1.18 CWE-770 14 3 ATLAS
MEDIUM

picklescan: bypass allows silent RCE in ML pipelines

GHSA-v7x6-rv5q-mhwc
--
Supply Chain Code Execution Model Framework
picklescan Patch: 0.0.25 CWE-184 3 6 ATLAS
MEDIUM

picklescan: numpy bypass enables RCE in ML model pipelines

GHSA-fj43-3qmq-673f
--
Supply Chain Code Execution Framework Model
picklescan Patch: 0.0.25 CWE-502 3 7 ATLAS
HIGH EXPLOIT AVAIL

picklescan: scanner bypass enables DNS data exfiltration

CVE-2025-46417
--
EPSS 0.2%
Supply Chain Data Extraction Data Leakage Framework Model
picklescan Patch: 0.0.25 CWE-184 3 6 ATLAS
CRITICAL KEV SCANNER

Langflow: Unauth RCE via code injection endpoint

CVE-2025-3248
9.8
EPSS 100.0%
Code Execution Auth Bypass Framework Agent
langflow CWE-94 5 ATLAS
CRITICAL EXPLOIT AVAIL

BentoML: unauthenticated RCE via insecure deserialization

CVE-2025-27520
9.8
EPSS 35.7%
Code Execution Supply Chain Framework Inference
bentoml CWE-502 20 5 ATLAS
HIGH EXPLOIT AVAIL

jupyterlab-git: command injection via malicious repo name

CVE-2025-30370
7.4
EPSS 0.6%
Code Execution Supply Chain Framework Plugin
jupyterlab-git Patch: 0.51.1 CWE-78 1.9K 4 ATLAS
LOW EXPLOIT AVAIL

PyTorch: memory corruption in CUDA caching allocator

CVE-2025-3136
3.3
EPSS 0.3%
DoS Framework Inference
pytorch CWE-787 24.4K 2 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in JIT flatbuffer loader

CVE-2025-3121
5.5
EPSS 0.3%
DoS Supply Chain Framework Inference
pytorch 24.4K 3 ATLAS
MEDIUM

OpenAI WP Plugin: broken access control on AI settings

CVE-2025-31843
4.3
EPSS 0.4%
Auth Bypass DoS Plugin API
3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: lstm_cell memory corruption, local code exec

CVE-2025-3001
5.3
EPSS 0.2%
Code Execution DoS Framework
torch Patch: 2.10.0 CWE-119 24.4K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in torch.jit.script compiler

CVE-2025-3000
5.3
EPSS 0.2%
Code Execution Supply Chain Framework Inference
torch Patch: 2.13.0 CWE-119 24.4K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in RNN sequence unpacking

CVE-2025-2999
5.3
EPSS 0.2%
Code Execution Data Extraction Supply Chain Framework Training Data Inference
torch Patch: 2.9.1 CWE-119 24.4K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: memory corruption in RNN pad_packed_sequence

CVE-2025-2998
5.3
EPSS 0.2%
Code Execution Supply Chain DoS Framework Training Data
torch CWE-119 24.4K 3 ATLAS
MEDIUM EXPLOIT AVAIL

PyTorch: DoS via mkldnn_max_pool2d resource leak

CVE-2025-2953
5.5
EPSS 0.2%
DoS Supply Chain Framework Inference Model
pytorch CWE-404 24.4K 3 ATLAS
MEDIUM EXPLOIT AVAIL

openairinterface5g: segfault enables DoS via crafted UE message

CVE-2025-26265
6.5
EPSS 0.4%
DoS Inference
openairinterface5g 18.3K 2 ATLAS
HIGH

Mesop: class pollution enables DoS and LLM jailbreak

CVE-2025-30358
8.1
EPSS 0.6%
Jailbreak DoS Auth Bypass Framework Agent
CWE-915 6 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