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
3,023

AI/ML CVEs Tracked

424

Critical

115

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 3023 results
CRITICAL SCANNER

vllm: security flaw enables exploitation

CVE-2026-22778
9.8
EPSS 3.7%
Code Execution Data Leakage Inference Framework API
vllm CWE-532 130 6 ATLAS
MEDIUM

picklescan: Deserialization enables RCE

GHSA-m7j5-r2p5-c39r
--
Supply Chain DoS Code Execution Framework Model Training Data
picklescan Patch: 1.0.1 CWE-502 3 4 ATLAS
HIGH

picklescan: Deserialization enables RCE

GHSA-9m3x-qqw2-h32h
--
Supply Chain Code Execution Model Framework
picklescan Patch: 1.0.1 CWE-502 3 6 ATLAS
CRITICAL EXPLOIT AVAIL

langroid: Code Injection enables RCE

CVE-2026-25481
--
EPSS 0.6%
Code Execution Prompt Injection Auth Bypass Agent Framework Plugin
langroid Patch: 0.59.32 CWE-94 4 6 ATLAS
HIGH EXPLOIT AVAIL

lollms: Access Control bypass enables privilege escalation

CVE-2026-1117
8.2
EPSS 0.4%
Auth Bypass DoS API Inference Framework
lollms Patch: 2.1.0 CWE-284 4 ATLAS
MEDIUM EXPLOIT AVAIL

llama-index-core: DoS causes service disruption

CVE-2025-6208
5.3
EPSS 0.4%
DoS Framework RAG
llama-index-core Patch: 0.12.41 CWE-400 1.2K 4 ATLAS
HIGH EXPLOIT AVAIL

text-generation: DoS causes service disruption

CVE-2026-0599
7.5
EPSS 22.5%
DoS Inference Framework API
text-generation Patch: 3.3.7 CWE-400 5 ATLAS
HIGH EXPLOIT AVAIL

mlflow: security flaw enables exploitation

CVE-2025-10279
7.0
EPSS 0.2%
Code Execution Supply Chain Framework Training Data
mlflow Patch: 3.4.0rc0 CWE-379 680 4 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
LOW

llama-stack: security flaw enables exploitation

CVE-2026-25211
3.2
EPSS 0.2%
Data Leakage Data Extraction RAG Framework
llama-stack Patch: 0.4.4 CWE-532 13 4 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 499 3 ATLAS
MEDIUM

Menu Panel: IDOR auth bypass exposes confidential data

CVE-2025-7013
5.7
EPSS 0.3%
Auth Bypass Data Extraction API Framework
Menu Panel 499 3 ATLAS
MEDIUM

agentos-taskweaver: Protection Bypass circumvents security controls

GHSA-gpx9-96j6-pp87
6.5
Prompt Injection Code Execution Auth Bypass Agent Framework Plugin
agentos-taskweaver CWE-693 6 ATLAS
HIGH EXPLOIT AVAIL

vllm: SSRF allows internal network access

CVE-2026-24779
7.1
EPSS 0.5%
Auth Bypass Data Extraction DoS Inference Framework API
vllm CWE-918 130 6 ATLAS
HIGH EXPLOIT AVAIL

pytorch: Code Injection enables RCE

CVE-2026-24747
8.8
EPSS 0.7%
Code Execution Supply Chain Framework Model
pytorch CWE-94 24.4K 6 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 16 9 ATLAS
MEDIUM EXPLOIT AVAIL

bentoml: Path Traversal enables file access

CVE-2026-24123
6.5
EPSS 0.4%
Supply Chain Data Extraction Framework Inference
bentoml CWE-22 20 8 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
UNKNOWN

langflow: Deserialization enables RCE

CVE-2026-0772
--
EPSS 0.9%
Code Execution Supply Chain Data Extraction Framework Agent RAG
langflow CWE-502 8 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