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

114

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 1321 results — High severity
HIGH

open-webui: RAG poisoning via unauthorized KB overwrite

CVE-2026-44554
8.1
EPSS 0.3%
Auth Bypass Model Poisoning Prompt Injection RAG API Framework
open-webui Patch: 0.9.0 CWE-862 4 8 ATLAS
HIGH

open-webui: auth bypass allows unrestricted model access

CVE-2026-44556
7.1
EPSS 0.3%
Auth Bypass DoS Data Extraction API Inference Model
open-webui Patch: 0.9.0 CWE-284 4 8 ATLAS
HIGH EXPLOIT AVAIL

open-webui: access control bypass via model chaining

CVE-2026-44555
7.6
EPSS 0.2%
Auth Bypass API Model Inference
open-webui Patch: 0.9.0 CWE-862 4 4 ATLAS
HIGH

open-webui: Redis cache poisoning enables cross-instance tool hijack

CVE-2026-44552
8.7
EPSS 0.3%
Supply Chain Data Extraction Prompt Injection Agent Plugin Framework
open-webui Patch: 0.9.0 CWE-668 4 6 ATLAS
HIGH

open-webui: stale Socket.IO role allows cross-user note R/W

CVE-2026-44553
8.1
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation API Framework
open-webui Patch: 0.9.0 CWE-384 4 5 ATLAS
HIGH EXPLOIT AVAIL

open-webui: XSS in model descriptions steals session tokens

CVE-2026-44721
7.3
EPSS 0.3%
Auth Bypass Code Execution Data Extraction API Framework
open-webui Patch: 0.9.0 CWE-79 4 5 ATLAS
HIGH

n8n-mcp: path traversal + SSRF exposes n8n API keys

GHSA-8g7g-hmwm-6rv2
8.3
Auth Bypass Data Extraction Data Leakage Agent Plugin
n8n-mcp Patch: 2.50.1 CWE-22 16 6 ATLAS
HIGH KEV SCANNER

LiteLLM: RCE via MCP test endpoint command injection

CVE-2026-42271
8.8
EPSS 83.0%
Code Execution Auth Bypass Framework API Inference
litellm CWE-77 6 5 ATLAS
HIGH

LiteLLM: SSTI in prompt template endpoint enables RCE

CVE-2026-42203
8.8
EPSS 0.4%
Code Execution Data Extraction API Inference
litellm CWE-1336 6 5 ATLAS
HIGH

gnutls: NUL-byte username bypasses RSA-PSK auth

CVE-2026-42010
7.1
EPSS 1.1%
Auth Bypass Inference
rhaiis/vllm-rocm-rhel9 130 3 ATLAS
HIGH

diffusers: trust_remote_code bypass enables silent RCE

CVE-2026-44513
8.8
EPSS 0.8%
Supply Chain Code Execution Framework Model
diffusers Patch: 0.38.0 CWE-94 425 4 ATLAS
HIGH

diffusers: silent RCE via None.py trust_remote_code bypass

GHSA-j7w6-vpvq-j3gm
8.8
Code Execution Supply Chain Framework Model
diffusers Patch: 0.38.0 CWE-94 425 6 ATLAS
HIGH

Aegra: cross-tenant IDOR hijacks user thread data

CVE-2026-44504
--
EPSS 0.3%
Auth Bypass Data Extraction Data Leakage Framework Agent
aegra-api Patch: 0.9.7 CWE-285 3.7K 5 ATLAS
HIGH EXPLOIT AVAIL

praisonai: RCE via unpatched tool_override exec_module

CVE-2026-44334
8.4
EPSS 0.2%
Code Execution Auth Bypass Supply Chain Agent Framework Plugin
praisonai Patch: 4.6.32 CWE-94 1 5 ATLAS
HIGH EXPLOIT AVAIL

praisonaiagents: SSRF via URL parser confusion bypass

CVE-2026-44335
--
EPSS 0.4%
Auth Bypass Data Extraction Agent Plugin
praisonaiagents Patch: 1.6.32 CWE-918 20 4 ATLAS
HIGH EXPLOIT AVAIL

GitPython: git config injection enables hook RCE

CVE-2026-44244
7.8
EPSS 0.2%
Supply Chain Code Execution Framework
GitPython Patch: 3.1.49 CWE-94 92 3 ATLAS
HIGH

JupyterLab: one-click RCE via notebook HTML cell output

CVE-2026-42557
8.8
EPSS 0.3%
Code Execution Social Engineering Supply Chain Framework Plugin
notebook Patch: 7.5.6 CWE-79 3.0K 8 ATLAS
HIGH EXPLOIT AVAIL

mistune: ReDoS exposes Jupyter/AI services to DoS

CVE-2026-33079
7.5
EPSS 0.5%
DoS Supply Chain Framework API
mistune Patch: 3.2.1 CWE-1333 1.9K 4 ATLAS
HIGH

JupyterLab: Extension allow-list bypass enables privesc

CVE-2026-42266
8.8
EPSS 0.6%
Supply Chain Auth Bypass Code Execution Framework Plugin
jupyterlab Patch: 4.5.7 CWE-20 1.9K 4 ATLAS
HIGH EXPLOIT AVAIL

PPTAgent: eval injection enables RCE via LLM prompt injection

CVE-2026-42079
8.6
EPSS 0.1%
Prompt Injection Code Execution Agent Framework
pptagent Patch: 1.1.36 CWE-95 5 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