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
3,021

AI/ML CVEs Tracked

424

Critical

113

New This Week

19

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 3021 results
HIGH

1Panel: CSRF in username change enables lockout

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

langgraph-checkpoint-sqlite: SQL Injection exposes database

CVE-2025-67644
7.3
EPSS 2.3%
Auth Bypass Data Extraction Framework Agent
langgraph-checkpoint-sqlite Patch: 3.0.1 CWE-89 3.7K 4 ATLAS
HIGH

NVIDIA: Deserialization enables RCE

CVE-2025-33213
8.8
EPSS 0.6%
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 16 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 83.8%
Auth Bypass Code Execution Framework Agent
langflow CWE-346 8 ATLAS
HIGH EXPLOIT AVAIL

open-webui: SSRF allows internal network access

CVE-2025-65958
8.5
EPSS 4.5%
Data Extraction Data Leakage Code Execution API RAG
open-webui Patch: 0.6.37 CWE-918 4 6 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 4 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-94 130 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
CRITICAL

ray: security flaw enables exploitation

CVE-2025-34351
--
EPSS 0.5%
Auth Bypass Code Execution Model Poisoning Framework Training Data Inference
ray CWE-304 620 8 ATLAS
CRITICAL KEV

ray: Code Injection enables RCE

CVE-2025-62593
--
EPSS 0.4%
Code Execution Auth Bypass Social Engineering Framework
ray Patch: 2.52.0 CWE-94 620 8 ATLAS
HIGH

langchain-core: security flaw enables exploitation

CVE-2025-65106
--
EPSS 0.5%
Prompt Injection Code Execution Data Extraction Framework Agent
langchain-core Patch: 1.0.7 CWE-1336 5.5K 7 ATLAS
HIGH EXPLOIT AVAIL

mlx: security flaw enables exploitation

CVE-2025-62609
7.5
EPSS 0.4%
DoS Supply Chain Framework Model
mlx CWE-476 363 5 ATLAS
CRITICAL EXPLOIT AVAIL

mlx: security flaw enables exploitation

CVE-2025-62608
9.1
EPSS 0.5%
Supply Chain Code Execution Data Extraction Framework Training Data
mlx CWE-122 363 6 ATLAS
HIGH EXPLOIT AVAIL

AI component: Arbitrary File Upload enables RCE

CVE-2025-12973
7.2
EPSS 0.9%
Code Execution Supply Chain Data Extraction Plugin API
6 ATLAS 1 incident

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