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
3,590

AI/ML CVEs Tracked

481

Critical

95

New This Week

24

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 3590 results
HIGH

functype-mcp-server: RCE via unsanitized pnpm install

CVE-2026-59176
7.8
Supply Chain Code Execution Agent Plugin
CWE-829 6 ATLAS
HIGH

nuxt-ollama: API key leaked in public SSR payload

CVE-2026-59158
7.5
Data Leakage Auth Bypass Framework API Inference
nuxt-ollama Patch: 1.3.1 CWE-522 1.8K 3 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: SSRF leaks Azure platform channel

CVE-2026-87999
7.1
EPSS 0.2%
Data Leakage RAG
open-webui Patch: 0.11.1 CWE-918 3 2 ATLAS
HIGH

Open WebUI: authZ flaw lets users kill shared KB configs

CVE-2026-87998
7.1
EPSS 0.3%
Auth Bypass DoS RAG API
open-webui Patch: 0.11.1 CWE-269 3 2 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: folder auth bypass injects rogue chats

CVE-2026-87997
4.3
EPSS 0.2%
Auth Bypass Framework API
open-webui Patch: 0.11.1 CWE-639 3 1 ATLAS
HIGH

Open WebUI: DNS rebinding SSRF exposes internal svcs

CVE-2026-87996
7.7
EPSS 0.2%
Data Leakage Auth Bypass RAG Plugin
open-webui Patch: 0.11.1 CWE-367 3 3 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: XSS in terminal preview hijacks user accounts

CVE-2026-87995
8.7
EPSS 0.2%
Code Execution Auth Bypass Framework Plugin
open-webui Patch: 0.11.1 CWE-79 3 1 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: channel authz gap allows message spoofing

CVE-2026-87994
4.3
EPSS 0.2%
Auth Bypass Framework Inference
open-webui Patch: 0.11.1 CWE-639 3 2 ATLAS
MEDIUM

Open WebUI: KB metadata leaks across tenants in 11 backends

CVE-2026-87017
4.3
EPSS 0.2%
Data Leakage Auth Bypass Privacy Violation RAG Framework
open-webui Patch: 0.11.1 CWE-200 3 3 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: OAuth wildcard bug hijacks admin sessions

CVE-2026-87016
8.1
EPSS 0.4%
Auth Bypass Privacy Violation Framework API
open-webui Patch: 0.11.1 CWE-155 3 2 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: session cookies leak to rogue tool server

CVE-2026-87015
6.8
EPSS 0.3%
Auth Bypass Data Leakage Agent Plugin API
open-webui Patch: 0.11.1 CWE-201 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: demoted admins keep socket access to all notes

CVE-2026-87014
6.5
EPSS 0.3%
Auth Bypass Privacy Violation Framework
open-webui Patch: 0.11.1 CWE-613 3 1 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: authenticated DoS via folder cycle

CVE-2026-87013
4.3
EPSS 0.3%
DoS Framework API
open-webui Patch: 0.11.1 CWE-835 3 3 ATLAS
MEDIUM

Open WebUI: type confusion suppresses all reminders

CVE-2026-87012
4.3
EPSS 0.3%
DoS Framework
open-webui Patch: 0.11.1 CWE-754 3
HIGH EXPLOIT AVAIL

Open WebUI: unauth DoS via OIDC logout handler

CVE-2026-87011
7.5
EPSS 0.4%
DoS Framework API
open-webui Patch: 0.11.1 CWE-405 3 2 ATLAS
HIGH

Chainlit: path traversal via sessionId wipes directories

CVE-2026-86099
8.2
EPSS 0.4%
DoS Auth Bypass Framework
chainlit 41 2 ATLAS
MEDIUM SCANNER

CyberPanel: AI Scanner endpoints leak admin usernames unauthenticated

CVE-2026-87820
5.3
EPSS 0.5%
Data Leakage Auth Bypass API Plugin
CWE-200 2 ATLAS
HIGH EXPLOIT AVAIL

SiYuan: stored XSS in notebook template paths

CVE-2026-87811
7.3
EPSS 0.2%
Code Execution Data Leakage Plugin
1 ATLAS
HIGH

WPBot: unauth stored XSS in chatbot conversation field

CVE-2026-83593
7.2
EPSS 0.3%
Auth Bypass Code Execution Data Leakage Plugin Agent
WPBot – AI ChatBot for Live Support, Lead Generation, AI Services CWE-79 1 ATLAS
HIGH

InsydeH2O: BIOS memory corruption enables local RCE

CVE-2026-12855
8.2
EPSS 0.1%
Code Execution Inference
InsydeH2O 27

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