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
4,307

AI/ML CVEs Tracked

533

Critical

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 983 results — Medium severity, no patch
MEDIUMEXPLOIT AVAIL

Dagster: path traversal exposes arbitrary file read via gRPC

CVE-2025-51481
6.6
EPSS 0.6%
Data ExtractionData LeakageFrameworkTraining Data
CWE-225 ATLAS
MEDIUM

DSpace: XXE injection enables server file disclosure

CVE-2025-53621
6.9
EPSS 0.4%
Data ExtractionSupply ChainAPITraining Data
5 ATLAS
MEDIUMEXPLOIT AVAIL

Transformers: ReDoS in DonutProcessor causes DoS

CVE-2025-3933
5.3
EPSS 0.5%
DoSFrameworkInference
transformersCWE-13339.8K4 ATLAS
MEDIUMEXPLOIT AVAIL

Contest Gallery WP Plugin: Stored XSS in OpenAI integration

CVE-2025-6716
6.4
EPSS 0.2%
Code ExecutionData LeakagePluginAPI
4 ATLAS
MEDIUMEXPLOIT AVAIL

OpenAI Operator: fullscreen spoofing captures credentials

CVE-2025-7021
6.5
EPSS 0.4%
Social EngineeringPrivacy ViolationAgentAPI
operator15.6K6 ATLAS
MEDIUMEXPLOIT AVAIL

Transformers: ReDoS in dynamic module loader causes DoS

CVE-2025-3264
5.3
EPSS 0.5%
DoSSupply ChainFrameworkModel
transformersCWE-13339.8K4 ATLAS
MEDIUMEXPLOIT AVAIL

Transformers: ReDoS in config loader causes serving DoS

CVE-2025-3263
5.3
EPSS 0.5%
DoSFramework
transformersCWE-13339.8K4 ATLAS
MEDIUM

n8n: broken authz enables cross-user workflow termination

CVE-2025-52554
4.3
EPSS 0.4%
Auth BypassDoSAgentFramework
n8n164 ATLAS
MEDIUMEXPLOIT AVAIL

LiteLLM: SQL injection in key management API

CVE-2025-45809
5.4
EPSS 0.3%
Data ExtractionAuth BypassAPIFramework
litellm65 ATLAS
MEDIUMEXPLOIT AVAIL

n8n: DoS via empty filesystem URI in binary-data API

CVE-2025-49595
4.9
EPSS 0.5%
DoSAgentFramework
n8n163 ATLAS
MEDIUMEXPLOIT AVAIL

Langchain-Chatchat: path traversal in file API exposes host FS

CVE-2025-6854
4.3
EPSS 0.6%
Data ExtractionData LeakageFrameworkAPIRAG
langchain-chatchatCWE-223.2K5 ATLAS
MEDIUM

n8n: open redirect enables phishing via login flow

CVE-2025-49592
5.4
EPSS 0.2%
Social EngineeringAuth BypassAgentFramework
n8n165 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: input validation DoS crashes inference worker

CVE-2025-48944
6.5
EPSS 0.6%
DoSInferenceAPIFramework
vllmCWE-20943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: ReDoS crashes inference server via malformed regex

CVE-2025-48943
6.5
EPSS 0.5%
DoSInferenceFramework
vllmCWE-248944 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: DoS via malformed JSON schema guided param

CVE-2025-48942
6.5
EPSS 0.6%
DoSInferenceAPI
vllmCWE-248943 ATLAS
MEDIUMEXPLOIT AVAIL

vLLM: ReDoS in tool parser causes service outage

CVE-2025-48887
6.5
EPSS 0.5%
DoSInferenceAPIFramework
vllmCWE-1333943 ATLAS
MEDIUM

A flaw was found in GNU Coreutils. The sort utility's begfield() function is vulnerable to a heap buffer under-read. The program may access memory outside the...

CVE-2025-5278
4.4
rhoai/odh-llama-stack-k8s-operator-rhel914
MEDIUMEXPLOIT AVAIL

transformers: ReDoS in GPT-NeoX Japanese tokenizer

CVE-2025-1194
6.5
EPSS 0.5%
DoSFramework
transformersCWE-13339.8K4 ATLAS
MEDIUM

n8n: stored XSS enables account takeover

CVE-2025-46343
5.4
EPSS 0.3%
Auth BypassCode ExecutionAgentFramework
n8n165 ATLAS
MEDIUMEXPLOIT AVAIL

PyTorch: DoS via ctc_loss resource mishandling

CVE-2025-3730
5.5
EPSS 0.3%
DoSFramework
pytorchCWE-40426.1K3 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