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

95

New This Week

25

In CISA KEV

Sort:Date CVSS EPSS KEV first Most exploited

Filter:All Critical High MediumKEV only Active exploitationHas patch No patch

Latest AI Security Threats

Showing 20 of 4307 results

HIGHEXPLOIT AVAIL

gradio: SSRF allows internal network access

CVE-2026-28416

Data ExtractionCode ExecutionFrameworkModelTraining Data

gradioCWE-9187359 ATLAS

gradio: Info Disclosure leaks sensitive data

CVE-2026-28415

Data ExtractionCode ExecutionAuth BypassFrameworkRAGAPI

gradioCWE-2007357 ATLAS

HIGHEXPLOIT AVAILSCANNER

gradio: security flaw enables exploitation

CVE-2026-28414

Code ExecutionData ExtractionFrameworkAPIModel

gradioCWE-367359 ATLAS

MEDIUMEXPLOIT AVAIL

gradio: Weak Credentials allow account compromise

CVE-2026-27167

Supply ChainModel PoisoningCode ExecutionFrameworkAgentAPI

gradioCWE-5227358 ATLAS

uv: ZIP parsing differential allows code execution

CVE-2025-13327

Supply ChainCode ExecutionFrameworkInference

rhaiis-preview/vllm-cuda-rhel9943 ATLAS

CRITICALEXPLOIT AVAIL

langflow: Code Injection enables RCE

CVE-2026-27966

Prompt InjectionCode ExecutionFrameworkRAGAgent

langflowCWE-9412 ATLAS

n8n: XSS enables session hijacking

CVE-2026-27578

Prompt InjectionData ExtractionCode ExecutionAgentRAGAPI

n8nCWE-791610 ATLAS

n8n: Code Injection enables RCE

CVE-2026-27577

Model PoisoningCode ExecutionSocial EngineeringAgentRAGAPI

n8nCWE-94169 ATLAS

n8n: Code Injection enables RCE

CVE-2026-27498

Model PoisoningCode ExecutionAgentRAGAPI

n8nCWE-941610 ATLAS

n8n: SQL Injection exposes database

CVE-2026-27497

Model PoisoningCode ExecutionAgentRAGAPI

n8nCWE-89169 ATLAS

n8n: Code Injection enables RCE

CVE-2026-27495

Code ExecutionSocial EngineeringAgentRAGAPI

n8nCWE-94169 ATLAS

n8n: security flaw enables exploitation

CVE-2026-27494

Code ExecutionAgentRAGAPI

n8nCWE-497169 ATLAS

n8n: Code Injection enables RCE

CVE-2026-27493

Code ExecutionAgentRAGAPI

n8nCWE-94166 ATLAS

langgraph-checkpoint: Deserialization enables RCE

CVE-2026-27794

Code ExecutionSupply ChainFrameworkAgent

langgraph-checkpointPatch: 4.0.0CWE-5024.1K4 ATLAS

LangChain: SSRF allows internal network access

CVE-2026-27795

Data ExtractionCode ExecutionDoSFrameworkRAGAgent

fickling: Allowlist Bypass evades input filtering

GHSA-mhc9-48gj-9gp3

Supply ChainCode ExecutionFrameworkModel

ficklingPatch: 0.1.8CWE-184627 ATLAS

fickling: security flaw enables exploitation

GHSA-mxhj-88fx-4pcv

Supply ChainCode ExecutionAuth BypassFrameworkModel

ficklingPatch: 0.1.8CWE-436626 ATLAS

mlflow: security flaw enables exploitation

CVE-2026-2635

Model PoisoningCode ExecutionAuth BypassFrameworkRAGModel

mlflowPatch: 3.8.0rc0CWE-139369510 ATLAS

TensorFlow: security flaw enables exploitation

CVE-2026-2492

Code ExecutionAuth BypassFrameworkRAGPlugin

mlflow: Path Traversal enables file access

CVE-2026-2033

Data ExtractionModel PoisoningCode ExecutionFrameworkRAGModel

mlflowPatch: 3.8.0rc0CWE-2269511 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