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

InsydeH2O UEFI: BIOS Shell allows Secure Boot bypass

CVE-2026-6485
8.2
EPSS 0.1%
Auth Bypass Code Execution Inference
InsydeH2O 27
MEDIUM

n8n Git node: config injection leaks local files

CVE-2026-86995
--
EPSS 0.3%
Data Leakage Privacy Violation Agent Plugin
n8n Patch: 1.123.76 CWE-22 3 ATLAS
MEDIUM

n8n: broken authZ leaks workflow IDs to any member

CVE-2026-86994
--
EPSS 0.2%
Auth Bypass Data Leakage Agent
n8n Patch: 1.123.76 CWE-862 1 ATLAS
MEDIUM

n8n: cross-project credential theft via Log Streaming

CVE-2026-86993
--
EPSS 0.3%
Auth Bypass Data Leakage Agent Plugin
n8n Patch: 1.123.76 CWE-862 3 ATLAS
MEDIUM

n8n: missing scope check leaks project member emails

CVE-2026-86085
--
EPSS 0.3%
Auth Bypass Privacy Violation Agent
n8n Patch: 2.38.2 CWE-862 2 ATLAS
MEDIUM

n8n: stale OIDC endpoint bypasses disabled SSO

CVE-2026-86084
--
EPSS 0.3%
Auth Bypass Agent
n8n Patch: 1.123.76 CWE-288 2 ATLAS
HIGH

n8n: code injection via legacy expression engine

CVE-2026-86083
--
EPSS 0.4%
Code Execution Supply Chain Framework Agent
n8n Patch: 1.123.76 CWE-94 3 ATLAS
HIGH

n8n: OpenAI node leaks API key via SSRF bypass

CVE-2026-86082
--
EPSS 0.2%
Auth Bypass Data Leakage Agent API
n8n Patch: 1.123.76 CWE-918 2 ATLAS
HIGH

n8n: ReDoS via Git node clone freezes instance

CVE-2026-86081
--
EPSS 0.3%
DoS Agent Framework
n8n Patch: 1.123.76 CWE-1333 2 ATLAS
MEDIUM

n8n: GitHub webhook signature bypass on 422 retry

CVE-2026-86080
--
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
n8n Patch: 1.123.76 CWE-347 2 ATLAS
MEDIUM

n8n: path traversal in Elasticsearch node leaks data

CVE-2026-86079
--
EPSS 0.3%
Auth Bypass Data Leakage Agent Plugin
n8n Patch: 1.123.76 CWE-22 2 ATLAS
MEDIUM

n8n: prototype pollution in AI workflow summary

CVE-2026-86078
--
EPSS 0.3%
DoS Agent Framework
n8n Patch: 2.38.2 CWE-1321 1 ATLAS
MEDIUM

n8n: chat token replay bypasses HITL approval gates

CVE-2026-86077
--
EPSS 0.3%
Auth Bypass Agent
n8n Patch: 2.38.2 CWE-862 2 ATLAS
HIGH

n8n: expression sandbox escape enables RCE

CVE-2026-86076
--
EPSS 0.4%
Code Execution Framework Agent
n8n Patch: 1.123.76 CWE-94 1 ATLAS
HIGH

n8n: unauth OAuth DCR fields exhaust DB storage

CVE-2026-86075
--
EPSS 0.3%
DoS Agent API
n8n Patch: 2.38.2 CWE-770 2 ATLAS
AWAITING NVD

n8n: Agent tool bypasses workflow caller restriction

CVE-2026-86996
--
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n Patch: 2.38.2 CWE-862 3 ATLAS
HIGH EXPLOIT AVAIL

winml-cli: RCE via wildcard CORS + trust-remote-code

CVE-2026-84452
--
EPSS 0.9%
Code Execution Auth Bypass Supply Chain Framework Inference Model
winml-cli Patch: 0.4.0 CWE-306 1.1K 4 ATLAS
HIGH

tiptap: ReDoS in Markdown attribute parsers

GHSA-j95f-988m-3j2f
--
DoS Framework
@tiptap/core Patch: 3.30.5 CWE-400 15.9K 2 ATLAS
MEDIUM

Auth0 AD/LDAP Connector: unauth local panel leaks AD creds

CVE-2026-85981
6.7
EPSS 0.1%
Auth Bypass Data Leakage Plugin
2 ATLAS
HIGH EXPLOIT AVAIL

NLTK tgrep ReDoS: single request hangs Python process

CVE-2026-80206
--
EPSS 0.3%
DoS Framework
nltk Patch: 3.10.3 CWE-1333 3.1K 3 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