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
2,387

AI/ML CVEs Tracked

341

Critical

358

New This Week

18

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 230 results — Critical severity, no patch
CRITICAL

OpenClaw: SSRF via Feishu extension exposes internal services

CVE-2026-28451
9.3
EPSS 0.3%
Prompt Injection Data Extraction Auth Bypass Agent Plugin
openclaw 4 5 ATLAS 1 incident
CRITICAL EXPLOIT AVAIL

langflow: Code Injection enables RCE

CVE-2026-27966
9.8
EPSS 33.7%
Prompt Injection Code Execution Framework RAG Agent
langflow CWE-94 12 ATLAS
CRITICAL

n8n: Code Injection enables RCE

CVE-2026-27577
9.9
EPSS 10.2%
Model Poisoning Code Execution Social Engineering Agent RAG API
n8n CWE-94 9 ATLAS
CRITICAL

n8n: Code Injection enables RCE

CVE-2026-27495
9.9
EPSS 0.6%
Code Execution Social Engineering Agent RAG API
n8n CWE-94 9 ATLAS
CRITICAL

n8n: security flaw enables exploitation

CVE-2026-27494
9.9
EPSS 0.4%
Code Execution Agent RAG API
n8n CWE-497 9 ATLAS
CRITICAL

n8n: Code Injection enables RCE

CVE-2026-27493
9.0
EPSS 1.1%
Code Execution Agent RAG API
n8n CWE-94 6 ATLAS
CRITICAL EXPLOIT AVAIL

smolagents: SSRF allows internal network access

CVE-2026-2654
9.8
EPSS 0.4%
Code Execution Data Extraction Auth Bypass Agent Framework Plugin
smolagents CWE-918 93 6 ATLAS
CRITICAL

Smart Panel: unauthenticated file upload enables RCE

CVE-2025-14014
9.8
EPSS 0.4%
Code Execution Auth Bypass Framework
Smart Panel 479 5 ATLAS
CRITICAL

n8n: Protection Bypass circumvents security controls

CVE-2026-25115
9.9
EPSS 0.5%
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
n8n CWE-693 7 ATLAS
CRITICAL

n8n: Command Injection enables RCE

CVE-2026-25053
9.9
EPSS 0.6%
Code Execution Data Extraction Auth Bypass Agent Framework Plugin
n8n CWE-78 9 ATLAS
CRITICAL

n8n: security flaw enables exploitation

CVE-2026-25052
9.9
EPSS 0.3%
Auth Bypass Data Extraction Data Leakage Agent Framework API
n8n CWE-367 9 ATLAS
CRITICAL

n8n: security flaw enables exploitation

CVE-2026-25049
9.9
EPSS 1.2%
Code Execution Data Extraction Auth Bypass Agent Framework API
n8n CWE-913 8 ATLAS
CRITICAL

vllm: security flaw enables exploitation

CVE-2026-22778
9.8
EPSS 3.3%
Code Execution Data Leakage Inference Framework API
vllm CWE-532 130 6 ATLAS
CRITICAL EXPLOIT AVAIL

cai-framework: Command Injection enables RCE

CVE-2026-25130
9.7
EPSS 0.8%
Prompt Injection Code Execution Agent Framework Plugin
CWE-78 9 ATLAS
CRITICAL EXPLOIT AVAIL

n8n: Code Injection enables RCE

CVE-2026-1470
9.9
EPSS 18.7%
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
n8n CWE-95 9 ATLAS
CRITICAL EXPLOIT AVAIL

Kalrav: Arbitrary File Upload enables RCE

CVE-2025-13374
9.8
EPSS 1.1%
Code Execution Auth Bypass Data Extraction Plugin Agent API
CWE-434 8 ATLAS
CRITICAL

vllm: Code Injection enables RCE

CVE-2026-22807
9.8
EPSS 0.5%
Supply Chain Code Execution Framework Inference Model
vllm CWE-94 130 7 ATLAS
CRITICAL EXPLOIT AVAIL

n8n: Code Injection enables RCE

CVE-2026-0863
9.9
EPSS 8.5%
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
n8n CWE-94 8 ATLAS
CRITICAL SCANNER

n8n: Code Injection enables RCE

CVE-2026-21877
9.9
EPSS 5.3%
Code Execution Auth Bypass Supply Chain Agent Framework Plugin
n8n CWE-94 9 ATLAS
CRITICAL KEV SCANNER

n8n: Input Validation flaw enables exploitation

CVE-2026-21858
10.0
EPSS 71.6%
Data Extraction Code Execution Auth Bypass Agent Framework API
n8n 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