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 497 results — Active exploitation, has patch
HIGH EXPLOIT AVAIL

Open WebUI: KaTeX fallback XSS steals admin session

CVE-2026-70492
8.7
EPSS 0.3%
Code Execution Data Leakage Auth Bypass Framework
open-webui Patch: 0.11.0 CWE-79 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

open-webui: shared tool source leaks hardcoded API keys

CVE-2026-70491
6.5
EPSS 0.3%
Data Leakage Auth Bypass Plugin Agent
open-webui Patch: 0.11.0 CWE-200 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: automation rule parsing freezes server

CVE-2026-70489
6.5
EPSS 0.4%
DoS Agent Framework
open-webui Patch: 0.11.0 CWE-400 3 3 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: iframe sandbox bypass = account takeover

CVE-2026-70486
8.2
EPSS 0.3%
Code Execution Data Leakage Auth Bypass Agent Framework
open-webui Patch: 0.11.0 CWE-79 3 4 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: NAT64 IPv6 trick bypasses SSRF filter, leaks metadata

CVE-2026-70485
7.1
EPSS 0.2%
Data Extraction Privacy Violation RAG API
open-webui Patch: 0.11.0 CWE-918 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: client-side SSRF via Vega chart rendering

CVE-2026-70480
4.1
EPSS 0.2%
Data Leakage Data Extraction Framework RAG
open-webui Patch: 0.11.0 CWE-918 3 2 ATLAS
LOW EXPLOIT AVAIL

Open WebUI: broken authz cancels other users' chats

CVE-2026-70483
3.1
EPSS 0.3%
Auth Bypass DoS Framework API
open-webui Patch: 0.11.0 CWE-862 3 2 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: OAuth token exchange enables takeover

CVE-2026-70482
8.1
EPSS 0.5%
Auth Bypass Privacy Violation Framework API
open-webui Patch: 0.11.0 CWE-287 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: members can edit/delete others' channel messages

CVE-2026-70481
5.4
EPSS 0.3%
Auth Bypass DoS Framework API
open-webui Patch: 0.11.0 CWE-284 3 1 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: Playwright SSRF leaks cloud metadata

CVE-2026-70479
7.7
EPSS 0.3%
Data Leakage Auth Bypass RAG Framework
open-webui Patch: 0.11.0 CWE-918 3 3 ATLAS
CRITICAL EXPLOIT AVAIL

Flowise: unauth OAuth refresh endpoint leaks access tokens

CVE-2026-70478
--
EPSS 0.5%
Auth Bypass Data Leakage Agent Plugin
flowise Patch: 3.1.3 CWE-200 4 ATLAS
UNKNOWN EXPLOIT AVAIL

Flowise: prompt injection bypasses sandbox for RCE

CVE-2026-70477
--
EPSS 0.8%
Prompt Injection Code Execution Agent Plugin
flowise-components Patch: 3.1.3 CWE-94 4 ATLAS
UNKNOWN EXPLOIT AVAIL

Flowise: billing IDOR lets tenants hijack Stripe subs

CVE-2026-70476
--
EPSS 0.3%
Auth Bypass Agent Framework
flowise Patch: 3.1.3 CWE-284 2 ATLAS
UNKNOWN EXPLOIT AVAIL

Flowise: missing authz lets users tamper executions

CVE-2026-70475
--
EPSS 0.3%
Auth Bypass Agent Framework
flowise Patch: 3.1.3 CWE-862 3 ATLAS
HIGH EXPLOIT AVAIL

Flowise: IDOR permite secuestrar credenciales OAuth2

CVE-2026-70474
--
EPSS 0.4%
Auth Bypass Data Leakage Framework Agent Plugin
flowise Patch: 3.1.3 CWE-863 4 ATLAS
UNKNOWN EXPLOIT AVAIL

Flowise: broken authz leaks Qdrant config, infra data

CVE-2026-70473
--
EPSS 0.3%
Auth Bypass Data Leakage Framework Agent RAG
flowise Patch: 3.1.3 CWE-200 4 ATLAS
HIGH EXPLOIT AVAIL

Flowise: broken auth exposes cross-tenant OpenAI keys

CVE-2026-70472
--
EPSS 0.3%
Auth Bypass Data Leakage Agent RAG API
flowise Patch: 3.1.3 CWE-285 4 ATLAS
UNKNOWN EXPLOIT AVAIL

Flowise: env-var bypass reinstates npx auto-exec RCE

CVE-2026-69263
--
EPSS 0.5%
Code Execution Supply Chain Agent Plugin
flowise-components Patch: 3.1.3 CWE-184 4 ATLAS
HIGH EXPLOIT AVAIL

Flowise: broken authz allows cross-type flow deletion

CVE-2026-69262
--
EPSS 0.3%
Auth Bypass DoS Agent Framework
flowise Patch: 3.1.3 CWE-863 1 ATLAS
UNKNOWN EXPLOIT AVAIL

Flowise: RCE via SQLite path overwrite + root Docker

CVE-2026-69259
--
EPSS 0.7%
Code Execution Agent Framework
flowise-components Patch: 3.1.3 CWE-94 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