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
4,331

AI/ML CVEs Tracked

535

Critical

108

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1295 results — High severity, no patch
HIGHEXPLOIT AVAIL

libtiff: arbitrary write via crafted TIFF image

CVE-2025-9900
8.8
EPSS 1.0%
Code ExecutionDoSInferenceModel
rhaiis/vllm-cuda-rhel9943 ATLAS
HIGHEXPLOIT AVAIL

Transformers: ReDoS in optimizer halts training pipelines

CVE-2025-6921
7.5
EPSS 0.5%
DoSFrameworkTraining Data
transformersCWE-4009.8K4 ATLAS
HIGHEXPLOIT AVAIL

Flowise: unauthenticated SSRF exposes internal network

CVE-2025-59527
7.5
EPSS 5.5%
Data ExtractionPrivacy ViolationAgentFramework
flowise4 ATLAS
HIGHEXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via model load

CVE-2025-9906
7.3
EPSS 0.2%
Code ExecutionSupply ChainFrameworkModel
kerasCWE-5024.1K6 ATLAS
HIGHEXPLOIT AVAIL

Keras: safe_mode bypass enables RCE via .h5 model files

CVE-2025-9905
7.3
EPSS 0.2%
Code ExecutionSupply ChainFrameworkModel
kerasCWE-9134.1K5 ATLAS
HIGHEXPLOIT AVAIL

picklescan: file extension bypass allows model RCE

CVE-2025-10155
7.8
EPSS 0.8%
Supply ChainCode ExecutionModelFramework
picklescanCWE-2035 ATLAS
HIGHEXPLOIT AVAIL

HuggingFace Transformers: ReDoS in MarianTokenizer

CVE-2025-6638
7.5
EPSS 0.6%
DoSSupply ChainFrameworkInference
transformersCWE-13339.8K4 ATLAS
HIGHEXPLOIT AVAIL

n8n: unrestricted file upload RCE via Chat Trigger

CVE-2025-56265
8.8
EPSS 0.6%
Code ExecutionData ExtractionAuth BypassFrameworkAgentPlugin
n8n165 ATLAS
HIGHEXPLOIT AVAIL

Langflow: privilege escalation to full superuser via CLI

CVE-2025-57760
8.8
EPSS 0.5%
Auth BypassCode ExecutionFrameworkAgent
langflowCWE-2695 ATLAS
HIGHEXPLOIT AVAIL

vLLM: unauthenticated DoS via oversized HTTP header

CVE-2025-48956
7.5
EPSS 0.6%
DoSInferenceAPIFramework
vllmCWE-400943 ATLAS
HIGH

Merlin Transformers4Rec: code injection via Python dep

CVE-2025-23298
7.8
EPSS 0.8%
Supply ChainCode ExecutionFramework
4 ATLAS
HIGH

Siemens TIA Portal/SIMATIC: DLL hijack in installer

CVE-2025-30033
7.8
EPSS 0.2%
Code ExecutionFramework
WinCC Panel Image Setup514
HIGHEXPLOIT AVAIL

Keras: safe mode bypass enables RCE via model load

CVE-2025-8747
7.8
EPSS 0.1%
Code ExecutionSupply ChainFrameworkModel
kerasCWE-5024.1K5 ATLAS
HIGH

WP Contest Gallery: Stored XSS exposes OpenAI API creds

CVE-2025-7725
7.2
EPSS 0.3%
Data ExtractionCode ExecutionPluginAPI
4 ATLAS
HIGH

lollms: timing attack enables credential enumeration

CVE-2025-6386
7.5
EPSS 0.4%
Auth BypassData ExtractionFrameworkAgent
lollmsCWE-2034 ATLAS
HIGHEXPLOIT AVAIL

Transformers: ReDoS in chat.py causes CPU exhaustion

CVE-2025-3262
7.5
EPSS 0.5%
DoSFramework
transformersCWE-13339.8K3 ATLAS
HIGHEXPLOIT AVAIL

Langchain-Chatchat: path traversal exposes system files

CVE-2025-6855
8.8
EPSS 0.6%
Data ExtractionCode ExecutionFrameworkRAG
langchain-chatchatCWE-223.2K5 ATLAS
HIGHEXPLOIT AVAIL

libssh: OOB read in SFTP handle leaks memory

CVE-2025-5318
8.1
EPSS 1.9%
Supply ChainData LeakageDoSInference
rhaiis/vllm-cuda-rhel9941 ATLAS
HIGHEXPLOIT AVAILSCANNER

Karel IP1211: path traversal exposes arbitrary files

CVE-2025-34023
--
EPSS 1.6%
Data LeakageAuth BypassPlugin
3 ATLAS
HIGH

Hive Support WP: OpenAI key theft + prompt hijack

CVE-2025-5018
7.1
EPSS 0.3%
Auth BypassData ExtractionPrompt InjectionAPIPlugin
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