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 2345 results — no patch
HIGH EXPLOIT AVAIL

Label Studio: org filter bypass leaks tenant storage

CVE-2026-85211
7.7
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation Training Data API
label-studio 2 3 ATLAS
HIGH EXPLOIT AVAIL

Label Studio: SSRF via webhooks hits cloud metadata

CVE-2026-85179
8.5
EPSS 0.2%
Data Leakage Data Extraction Training Data Framework
label-studio 2 3 ATLAS
UNKNOWN

n8n: IDOR exposes workflow data across projects

CVE-2026-85173
--
EPSS 0.2%
Auth Bypass Data Leakage Privacy Violation Agent API
n8n 3 ATLAS
UNKNOWN

n8n: SSRF bypass via uri/url validation mismatch

CVE-2026-85172
--
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n CWE-918 2 ATLAS
UNKNOWN

n8n: plaintext credential leak via error logging

CVE-2026-85171
--
EPSS 0.3%
Data Leakage Privacy Violation Agent Plugin
n8n 3 ATLAS
UNKNOWN

n8n: local file read & SSRF via Gmail/Brevo nodes

CVE-2026-85170
--
EPSS 0.2%
Data Extraction Data Leakage Agent Plugin
n8n CWE-20 3 ATLAS
HIGH

n8n: $fromAI sandbox escape enables RCE

CVE-2026-85169
--
EPSS 0.5%
Code Execution Auth Bypass Agent Framework
n8n CWE-94 4 ATLAS
UNKNOWN

n8n: Git node RCE via poisoned filter/merge config

CVE-2026-85168
--
EPSS 0.5%
Code Execution Supply Chain Agent Plugin
n8n 3 ATLAS
UNKNOWN

n8n: query injection turns lookup into full DB read

CVE-2026-85167
--
EPSS 0.2%
Data Extraction Data Leakage Auth Bypass Agent Plugin
n8n CWE-943 2 ATLAS
UNKNOWN

n8n: credential theft via unvalidated workflow node

CVE-2026-85166
--
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n 3 ATLAS
UNKNOWN

n8n: expression sandbox bypass mutates host globals

CVE-2026-85165
--
EPSS 0.3%
Code Execution Agent Framework
n8n CWE-95 3 ATLAS
HIGH

InsydeH2O UEFI: HDD password stored in plaintext

CVE-2021-38489
8.2
EPSS 0.1%
Data Leakage Privacy Violation Inference
InsydeH2O 27
MEDIUM

InsydeH2O UEFI: buffer overflow in PlatformLangCodes var

CVE-2021-43614
6.7
EPSS 0.1%
DoS Inference
InsydeH2O 27 1 ATLAS
MEDIUM

InsydeH2O UEFI: password hashes exposed, privesc risk

CVE-2021-43613
6.5
EPSS 0.1%
Data Leakage Auth Bypass Inference
InsydeH2O 27 1 ATLAS
MEDIUM

LiteLLM: param injection leaks provider API keys

CVE-2026-84377
6.5
EPSS 0.3%
Data Leakage Auth Bypass API Inference
litellm CWE-918 6 3 ATLAS
MEDIUM

APM Server: memory-exhaustion DoS via source maps

CVE-2026-78594
4.9
EPSS 0.3%
DoS Framework
Apm Server 1 ATLAS
HIGH

Craft CMS: auth bypass enables admin takeover

CVE-2026-84801
8.8
EPSS 0.2%
Auth Bypass Framework
MEDIUM

Kibana: missing authz leaks APM server credentials

CVE-2026-78608
6.5
EPSS 0.2%
Auth Bypass Data Leakage Plugin API
1 ATLAS
MEDIUM

Filament: stale TOTP code stays valid, bypassing MFA reuse block

CVE-2026-84306
6.5
EPSS 0.4%
Auth Bypass Framework
CWE-294
HIGH

SageMaker: HMAC leak allows forged pipeline code execution

CVE-2026-83551
7.2
EPSS 0.4%
Code Execution Auth Bypass Data Leakage API Framework
sagemaker 50 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