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 400 results — Medium severity, has patch
MEDIUM

CAPM3: cross-namespace auth bypass exposes K8s secrets

GHSA-rf84-wr5g-m3rp
5.5
Auth Bypass Data Leakage Framework
github.com/metal3-io/cluster-api-provider-metal3 Patch: 1.11.8 CWE-863 3 ATLAS
MEDIUM EXPLOIT AVAIL

local-deep-research: SSRF via URL parser differential bypass

CVE-2026-46526
5.0
EPSS 0.2%
Auth Bypass Data Extraction Agent
local-deep-research Patch: 1.6.10 CWE-918 3 ATLAS
MEDIUM

Kirby CMS: auth bypass leaks admin emails via content lock

CVE-2026-45334
--
EPSS 0.2%
Data Extraction Privacy Violation Auth Bypass Framework
getkirby/cms Patch: 4.9.1 CWE-862 499 4 ATLAS
MEDIUM EXPLOIT AVAIL

Gradio: cookie injection hijacks cross-Space sessions

CVE-2026-48545
6.8
EPSS 0.4%
Auth Bypass Privacy Violation Data Leakage Inference Framework
gradio Patch: 6.15.0 CWE-384 673 3 ATLAS
MEDIUM

Spring AI: path traversal via LLM-chosen filenames

CVE-2026-41863
6.5
EPSS 0.4%
Code Execution Prompt Injection Framework Agent
org.springframework.ai:spring-ai-anthropic Patch: 1.1.7 CWE-22 6.3K 3 ATLAS
MEDIUM EXPLOIT AVAIL

MLflow: missing authz exposes all model versions

CVE-2026-2734
6.5
EPSS 0.4%
Auth Bypass Data Extraction Privacy Violation Framework Model
mlflow Patch: 3.10.0 CWE-284 680 4 ATLAS
MEDIUM

Flowise: cross-workspace chatflow config disclosure

GHSA-c2c9-mfw7-p8hw
--
Auth Bypass Data Extraction Agent Framework
flowise Patch: 3.1.2 CWE-863 5 ATLAS
MEDIUM

Flowise: mass assignment bypasses password controls

GHSA-59fh-9f3p-7m39
--
Auth Bypass Agent
flowise Patch: 3.1.2 CWE-915 4 ATLAS
MEDIUM

Flowise: hardcoded CORS wildcard enables drive-by credential abuse

GHSA-m837-xvxr-vqwg
--
Auth Bypass Data Extraction Agent API
flowise Patch: 3.1.2 CWE-942 4 ATLAS
MEDIUM

n8n: path traversal bypasses file access restriction

GHSA-2vx9-7wpg-88jq
6.4
Data Extraction Auth Bypass Code Execution Agent Framework Plugin
n8n Patch: 2.19.3 CWE-22 16 5 ATLAS
MEDIUM

n8n-mcp: telemetry leak exposes workflow URL secrets

CVE-2026-45582
6.5
EPSS 0.3%
Data Leakage Privacy Violation Agent Plugin
n8n-mcp Patch: 2.51.3 CWE-201 16 3 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: unauth endpoint drains embedding budget/DoS

CVE-2026-45667
6.5
EPSS 0.3%
Auth Bypass DoS Inference API
open-webui Patch: 0.8.0 CWE-862 4 5 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: IDOR exposes cross-user note data

CVE-2026-45666
6.5
EPSS 0.3%
Auth Bypass Data Extraction Privacy Violation API Framework
open-webui Patch: 0.8.11 CWE-639 4 4 ATLAS
MEDIUM EXPLOIT AVAIL SCANNER

Open WebUI: unauthenticated RAG config leaks AI pipeline

CVE-2026-45397
5.3
EPSS 0.8%
Auth Bypass Data Extraction RAG Framework
open-webui Patch: 0.9.5 CWE-306 4 6 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: mass assignment enables leaderboard poisoning

CVE-2026-45396
5.4
EPSS 0.3%
Auth Bypass Model Poisoning Privacy Violation Framework Model
open-webui Patch: 0.9.5 CWE-915 4 5 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: system prompt leakage via model read API

CVE-2026-45387
4.3
EPSS 0.2%
Data Leakage Auth Bypass Privacy Violation Model API Framework
open-webui Patch: 0.9.5 CWE-200 4 4 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: auth bypass lets read-only users pin messages

CVE-2026-45386
4.3
EPSS 0.2%
Auth Bypass API Agent
open-webui Patch: 0.9.5 CWE-639 4 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: IDOR lets members tamper with admin messages

CVE-2026-45385
4.3
EPSS 0.2%
Auth Bypass Privacy Violation API Framework
open-webui Patch: 0.9.5 CWE-639 4 3 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: auth bypass exposes admin-restricted models

CVE-2026-45365
5.4
EPSS 0.2%
Auth Bypass Inference API
open-webui Patch: 0.8.11 CWE-285 4 4 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: admin system prompts exposed to all users

CVE-2026-45351
6.5
EPSS 0.3%
Data Leakage Auth Bypass Data Extraction API Model Framework
open-webui Patch: 0.8.9 CWE-200 4 4 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