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
2,393

AI/ML CVEs Tracked

342

Critical

305

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 1566 results — no patch
HIGH

keras: File Control enables path manipulation

CVE-2026-1669
7.5
EPSS 0.3%
Data Extraction Code Execution Framework RAG API
keras CWE-73 1.6K 8 ATLAS
MEDIUM

langchain_community: SSRF allows internal network access

CVE-2026-26019
4.1
EPSS 0.4%
Data Extraction Framework RAG Agent
langchain_community CWE-918 2.7K 8 ATLAS
LOW

langchain-core: SSRF allows internal network access

CVE-2026-26013
3.7
EPSS 0.4%
Data Extraction Framework RAG Agent
langchain_core CWE-918 2.7K 6 ATLAS
MEDIUM

GnuTLS: TLS cert parsing DoS hits vllm inference

CVE-2025-14831
5.3
EPSS 0.6%
DoS Inference
rhaiis/vllm-cuda-rhel9 130 3 ATLAS
MEDIUM

n8n: Input Validation flaw enables exploitation

CVE-2026-25631
6.5
EPSS 0.3%
Code Execution Social Engineering Agent RAG API
n8n CWE-20 7 ATLAS
MEDIUM EXPLOIT AVAIL

OpenClaw: path traversal enables arbitrary file read

CVE-2026-25475
6.5
EPSS 0.7%
Data Extraction Privacy Violation Supply Chain Agent Plugin
openclaw CWE-22 4 5 ATLAS 1 incident
HIGH

n8n: Input Validation flaw enables exploitation

CVE-2026-21893
7.2
EPSS 1.3%
Code Execution Social Engineering Agent RAG API
n8n CWE-20 10 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
HIGH

n8n: Arbitrary File Upload enables RCE

CVE-2026-25056
8.8
EPSS 0.7%
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
n8n CWE-434 8 ATLAS
HIGH

n8n: Path Traversal enables file access

CVE-2026-25055
8.1
EPSS 1.7%
Code Execution Auth Bypass Agent Framework
n8n CWE-22 7 ATLAS
MEDIUM

n8n: XSS enables session hijacking

CVE-2026-25054
5.4
EPSS 0.2%
Auth Bypass Code Execution Data Extraction Agent Framework API
n8n CWE-79 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
MEDIUM

n8n: XSS enables session hijacking

CVE-2026-25051
5.4
EPSS 0.2%
Code Execution Auth Bypass Data Extraction Agent Framework API
n8n CWE-79 6 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
HIGH

n8n: Info Disclosure leaks sensitive data

CVE-2025-61917
7.7
EPSS 0.4%
Data Extraction Data Leakage Privacy Violation Agent Framework API
n8n CWE-200 5 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
HIGH EXPLOIT AVAIL

agpt: Code Injection enables RCE

CVE-2026-24780
8.8
EPSS 1.1%
Code Execution Auth Bypass Agent Framework API
CWE-94 7 ATLAS
MEDIUM

Menu Panel: session fixation enables session hijacking

CVE-2025-7014
5.7
EPSS 0.3%
Auth Bypass Data Extraction Framework
Menu Panel 479 3 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