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 1049 results — Medium severity
MEDIUM

praisonaiagents: unauth SSE endpoint enables event injection

GHSA-35w5-pcw4-jx94
4.3
Auth Bypass Data Leakage Agent Framework
praisonaiagents Patch: 1.6.59 CWE-306 20 4 ATLAS
MEDIUM

marimo: reflected XSS enables JS injection in notebooks

CVE-2026-54386
6.1
EPSS 0.2%
Code Execution Data Extraction Framework
marimo Patch: 0.23.9 CWE-79 3.0K 3 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: Yjs auth bypass exposes all user notes

CVE-2026-54022
5.3
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation API Framework
open-webui Patch: 0.8.11 CWE-706 4 5 ATLAS
MEDIUM

open-webui: auth bypass reaches restricted Ollama backends

CVE-2026-54021
6.3
EPSS 0.2%
Auth Bypass Inference API
open-webui Patch: 0.9.6 CWE-863 4 4 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: RAG ACL bypass exposes private KB chunks

CVE-2026-54019
6.5
EPSS 0.3%
Auth Bypass Data Extraction Data Leakage RAG Framework
open-webui Patch: 0.9.6 CWE-862 4 5 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: BOLA exposes private knowledge base files

CVE-2026-54016
4.3
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation Agent RAG Framework
open-webui Patch: 0.9.6 CWE-862 4 6 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: IDOR exposes private prompt history

CVE-2026-54015
6.4
EPSS 0.2%
Auth Bypass Data Extraction Privacy Violation API Framework
open-webui Patch: 0.9.6 CWE-639 4 4 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: path traversal exposes sibling dirs

CVE-2026-54014
4.3
EPSS 0.3%
Data Extraction Inference
open-webui Patch: 0.9.6 CWE-22 4 3 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: cross-user file read via auth bypass

CVE-2026-54009
6.5
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation API Framework
open-webui Patch: 0.9.6 CWE-639 4 4 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: auth bypass allows cross-user calendar injection

CVE-2026-54006
4.3
EPSS 0.2%
Auth Bypass Social Engineering Privacy Violation Framework
open-webui Patch: 0.9.6 CWE-639 4 5 ATLAS
MEDIUM

vLLM: decompression bomb OOM via audio endpoint

CVE-2026-54233
6.5
EPSS 0.4%
DoS Inference API
vllm Patch: 0.24.0 CWE-409 130 3 ATLAS
MEDIUM EXPLOIT AVAIL SCANNER

vLLM: heap address leak enables ASLR bypass

CVE-2026-54236
5.3
EPSS 0.8%
Data Leakage Code Execution Inference API
vllm Patch: 0.24.0 CWE-532 130 3 ATLAS
MEDIUM

vllm: EXIF/tRNS preprocessing gap enables adversarial input

GHSA-8jr5-v98p-w75m
4.8
Adversarial Examples Prompt Injection Inference Framework
vllm CWE-436 130 4 ATLAS
MEDIUM

vLLM: NaN/Inf bypass crashes GPU inference workers

CVE-2026-54235
6.5
EPSS 0.3%
DoS Inference
vllm Patch: 0.24.0 CWE-1287 130 3 ATLAS
MEDIUM

n8n: viewer role can start/cancel/delete eval workflow runs

GHSA-664h-gpgq-h6xx
5.4
Auth Bypass DoS Agent Framework
n8n Patch: 1.123.55 CWE-863 16 3 ATLAS
MEDIUM

vLLM: image metadata mishandling corrupts multimodal inputs

CVE-2026-12491
4.8
EPSS 0.2%
Adversarial Examples DoS Inference Model
rhaiis/vllm-cpu-rhel9 130 4 ATLAS
MEDIUM

n8n: decompression bomb DoS via public webhook

CVE-2026-54314
--
EPSS 0.4%
DoS Agent Framework
n8n Patch: 2.24.0 CWE-409 16 4 ATLAS
MEDIUM

pydantic-ai: SSRF IPv6 bypass exposes cloud IAM creds

CVE-2026-48782
6.8
EPSS 0.3%
Data Extraction Auth Bypass Agent Framework
pydantic-ai Patch: 1.102.0 CWE-918 483 4 ATLAS
MEDIUM

n8n: read-only users can trigger workflow execution via API

GHSA-h3jj-5f3v-3685
6.4
Auth Bypass Agent
n8n Patch: 2.26.2 CWE-863 16 3 ATLAS
MEDIUM

n8n: AST bypass leaks env vars in Python Task Runner

GHSA-jwm3-qcfw-c5pp
5.0
Data Leakage Code Execution Auth Bypass Agent Framework
n8n Patch: 2.26.2 CWE-693 16 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