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
3,631

AI/ML CVEs Tracked

484

Critical

94

New This Week

25

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 2358 results — no patch
HIGH KEV SCANNER

n8n: security flaw enables exploitation

CVE-2025-68613
8.8
EPSS 99.1%
Code Execution Auth Bypass Data Extraction Agent Framework Plugin
n8n CWE-913 9 ATLAS
HIGH EXPLOIT AVAIL

langflow: File Control enables path manipulation

CVE-2025-68478
7.1
EPSS 4.1%
Code Execution Auth Bypass Framework Agent
langflow CWE-73 5 ATLAS
MEDIUM EXPLOIT AVAIL

langflow: SSRF allows internal network access

CVE-2025-68477
6.5
EPSS 6.3%
Data Extraction Auth Bypass Privacy Violation Framework Agent API
langflow CWE-918 8 ATLAS
HIGH EXPLOIT AVAIL

nbconvert: security flaw enables exploitation

CVE-2025-53000
--
EPSS 0.3%
Code Execution Supply Chain Framework
CWE-427 4 ATLAS
MEDIUM

anythingllm: Missing Auth allows unauthenticated access

CVE-2025-63390
5.3
EPSS 0.6%
Auth Bypass Data Extraction Privacy Violation API Framework Agent
7 ATLAS
CRITICAL

ollama: Missing Auth allows unauthenticated access

CVE-2025-63389
9.8
EPSS 0.7%
Auth Bypass Data Extraction Supply Chain Inference API Model
ollama 1.8K 9 ATLAS
CRITICAL EXPLOIT AVAIL

cai-framework: Command Injection enables RCE

CVE-2025-67511
9.6
EPSS 2.0%
Code Execution Prompt Injection Agent Framework
CWE-77 7 ATLAS
MEDIUM

1Panel: CSRF allows unauthorized panel rename

CVE-2025-34430
--
EPSS 0.2%
Auth Bypass Social Engineering API
HIGH

1Panel: CSRF in username change enables lockout

CVE-2025-34410
--
EPSS 0.2%
DoS Auth Bypass Inference
HIGH

NVIDIA: Deserialization enables RCE

CVE-2025-33213
8.8
EPSS 0.7%
Code Execution Supply Chain Data Extraction Framework Training Data Model
CWE-502 6 ATLAS
HIGH EXPLOIT AVAIL

n8n: security flaw enables exploitation

CVE-2025-65964
8.8
EPSS 0.7%
Code Execution Supply Chain Agent Framework
n8n 6 ATLAS
MEDIUM EXPLOIT AVAIL

AI component: SQL Injection exposes database

CVE-2025-13922
6.5
EPSS 0.3%
Data Extraction Auth Bypass Plugin API
5 ATLAS
HIGH KEV SCANNER

langflow: security flaw enables exploitation

CVE-2025-34291
8.8
EPSS 83.6%
Auth Bypass Code Execution Framework Agent
langflow CWE-346 8 ATLAS
UNKNOWN

Anthropic: Protection Bypass circumvents security controls

CVE-2025-66479
--
EPSS 0.2%
Auth Bypass Code Execution Data Extraction Agent Framework API
6 ATLAS
LOW EXPLOIT AVAIL

open-webui: Access Control bypass enables privilege escalation

CVE-2025-63681
--
EPSS 0.3%
Auth Bypass DoS API Inference Framework
open-webui CWE-284 3 4 ATLAS
HIGH EXPLOIT AVAIL

mcp-server-kubernetes: Command Injection enables RCE

CVE-2025-66404
8.8
EPSS 1.5%
Code Execution Prompt Injection Auth Bypass Agent Plugin Framework
7 ATLAS
MEDIUM

taxopress: SQL Injection exposes database

CVE-2025-13359
6.5
EPSS 0.3%
Data Extraction Privacy Violation Plugin API
5 ATLAS
MEDIUM

taxopress: Missing Auth allows unauthorized operations

CVE-2025-13354
4.3
EPSS 0.3%
Auth Bypass Plugin API
4 ATLAS
HIGH

vllm: Code Injection enables RCE

CVE-2025-66448
8.8
EPSS 0.7%
Supply Chain Code Execution Framework Inference Model
vllm CWE-94 92 8 ATLAS
UNKNOWN EXPLOIT AVAIL

Keras: Path Traversal enables file access

CVE-2025-12638
--
EPSS 0.7%
Supply Chain Code Execution Framework Training Data
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