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
3,018

AI/ML CVEs Tracked

424

Critical

113

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 3018 results
HIGH

n8n: Git node bypass leaks arbitrary local repos

GHSA-gf29-4f56-r2jf
--
Auth Bypass Data Leakage Agent Plugin
n8n Patch: 1.123.67 CWE-22 16 2 ATLAS
HIGH

n8n: AI node credential allowlist bypass leaks secrets

GHSA-64xh-79j6-r5v8
--
Auth Bypass Data Leakage Agent API
n8n Patch: 2.32.1 CWE-863 16 4 ATLAS
HIGH

n8n: auth bypass via embed login token exchange

GHSA-8342-988q-86cr
--
Auth Bypass Data Leakage Agent Framework
n8n Patch: 2.32.1 CWE-345 16 2 ATLAS
MEDIUM EXPLOIT AVAIL

InvokeAI: unauthenticated directory enumeration flaw

CVE-2026-65012
5.3
EPSS 0.3%
Auth Bypass Data Leakage API Framework
invokeai CWE-306 3 ATLAS
HIGH

FFmpeg: double-free in NVDEC decoder enables RCE

CVE-2026-64832
8.8
EPSS 0.3%
Code Execution DoS Inference Training Data
2 ATLAS
MEDIUM

n8n: GCP service account key leaks via JWT header

CVE-2026-65599
--
EPSS 0.2%
Data Leakage Auth Bypass Agent API
n8n Patch: 1.123.64 CWE-312 16 3 ATLAS
HIGH

n8n: Git clone TOCTOU race allows RCE via symlink swap

CVE-2026-65598
--
EPSS 0.2%
Code Execution Auth Bypass Supply Chain Agent Plugin
n8n Patch: 1.123.64 CWE-367 16 4 ATLAS
HIGH

n8n: DOM XSS in preview hijacks editor session

CVE-2026-65597
--
EPSS 0.2%
Code Execution Auth Bypass Agent API
n8n Patch: 1.123.64 CWE-79 16 2 ATLAS
MEDIUM

n8n: GraphQL node bypasses domain allowlist, leaks creds

CVE-2026-65596
--
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n Patch: 1.123.64 CWE-863 16 4 ATLAS
HIGH

n8n: Token Exchange bug grants admin API access

CVE-2026-65595
--
EPSS 0.5%
Auth Bypass Code Execution Agent API
n8n Patch: 2.30.1 CWE-269 16 3 ATLAS
MEDIUM

n8n: authz bypass hijacks other users' MCP workflows

CVE-2026-65594
--
EPSS 0.3%
Auth Bypass Data Leakage Privacy Violation Agent Plugin
n8n Patch: 2.30.1 CWE-863 16 4 ATLAS
MEDIUM

n8n: SSRF bypass in dynamic-node-parameters endpoint

CVE-2026-65593
--
EPSS 0.1%
Auth Bypass Data Extraction Agent API
n8n Patch: 1.123.64 CWE-918 16 2 ATLAS
HIGH

n8n: stored XSS via javascript: URI in Resource Locator

CVE-2026-65592
--
EPSS 0.2%
Code Execution Social Engineering Agent Plugin
n8n Patch: 1.123.64 CWE-79 16 4 ATLAS
HIGH

n8n: expression sanitizer bypass leads to host RCE

CVE-2026-65591
--
EPSS 0.5%
Code Execution Auth Bypass Agent Framework
n8n Patch: 1.123.64 CWE-917 16 4 ATLAS
MEDIUM

n8n computer-use: unsandboxed shell on Linux/Windows

CVE-2026-65590
--
EPSS 0.3%
Code Execution Data Leakage Agent Plugin
n8n Patch: 2.30.1 CWE-78 16 4 ATLAS
MEDIUM

n8n: plaintext credential leak in LLM node logs

CVE-2026-65589
--
EPSS 0.4%
Data Leakage Privacy Violation Agent Plugin API
n8n Patch: 1.123.64 CWE-532 16 3 ATLAS
HIGH

n8n: SSO instance-role provisioning grants owner

CVE-2026-65016
--
EPSS 0.3%
Auth Bypass Data Leakage Agent Framework
n8n Patch: 1.123.64 CWE-639 16 3 ATLAS
HIGH

n8n: Project Viewer escalates via AI Agent tool

CVE-2026-65015
--
EPSS 0.3%
Auth Bypass Code Execution Data Leakage Agent Plugin
n8n Patch: 2.30.1 CWE-863 16 4 ATLAS
MEDIUM

n8n: unauth DELETE cancels test webhook sessions

CVE-2026-65014
--
EPSS 0.3%
Auth Bypass DoS Agent
n8n Patch: 2.27.4 CWE-306 16 2 ATLAS
HIGH

Ollama: crafted GGUF file crashes inference server

CVE-2026-65315
7.5
EPSS 0.6%
DoS Inference Model
ollama CWE-789 1.7K 2 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