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
3,628

AI/ML CVEs Tracked

484

Critical

99

New This Week

25

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 1042 results — High severity, no patch
HIGH EXPLOIT AVAIL

SiYuan: brute-force bypass of notebook publish passwords

CVE-2026-73045
7.5
EPSS 0.3%
Auth Bypass Plugin
CWE-307 2 ATLAS
HIGH

JupyterLab: missing await bypasses extension allowlist

CVE-2026-73626
0.0
EPSS 0.2%
Supply Chain Auth Bypass Code Execution Plugin Framework
jupyterlab 1.9K 3 ATLAS
HIGH EXPLOIT AVAIL

SiYuan: missing authz exposes filtered DB rows

CVE-2026-73608
8.6
EPSS 0.2%
Auth Bypass Data Leakage API RAG
2 ATLAS
HIGH

OneCompression: RCE via malicious .pt checkpoint load

CVE-2026-73325
7.8
EPSS 0.3%
Code Execution Supply Chain Model Framework
CWE-502 4 ATLAS
HIGH

snowflake.core: injection enables privilege escalation

CVE-2026-19594
8.1
EPSS 0.4%
Auth Bypass API Framework
HIGH

Velociraptor: VQL auth-reset lets analyst gain investigator role

CVE-2026-64954
8.2
EPSS 0.2%
Auth Bypass Agent
HIGH

InsydeH2O UEFI: unverified boot allows local code execution

CVE-2026-6484
8.2
EPSS 0.1%
Code Execution Supply Chain Inference
InsydeH2O 27
HIGH

Sub2API: path traversal leaks pooled AI credentials

CVE-2026-73079
8.5
EPSS 0.3%
Auth Bypass Data Leakage API Inference
3 ATLAS
HIGH EXPLOIT AVAIL

TypeBot: guest role exfiltrates OpenAI keys via SSRF

CVE-2026-48766
7.6
EPSS 0.3%
Auth Bypass Data Leakage API
CWE-200 2 ATLAS
HIGH

Velociraptor: path traversal corrupts ACL/hunt metadata

CVE-2026-18640
7.1
EPSS 0.3%
Auth Bypass DoS API
HIGH

n8n: SQL injection via PostgresTrigger node

CVE-2026-72775
8.8
EPSS 0.3%
Code Execution Data Leakage Agent Plugin
n8n CWE-89 1 ATLAS
HIGH

n8n: path traversal leaks arbitrary local files

CVE-2026-72773
7.7
EPSS 0.4%
Auth Bypass Data Leakage Agent Plugin
n8n CWE-22 4 ATLAS
HIGH

n8n: SSRF bypass in MCP Client node exposes internal hosts

CVE-2026-72768
8.3
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
n8n CWE-918 3 ATLAS
HIGH

n8n: Send Email node type confusion enables SSRF, LFI

CVE-2026-72766
7.5
EPSS 0.3%
Data Leakage Data Extraction Framework Agent
n8n CWE-843 2 ATLAS
HIGH

n8n: SQL injection via Snowflake node Execute Query

CVE-2026-72750
8.8
EPSS 0.3%
Code Execution Data Extraction Agent Plugin
n8n CWE-89 1 ATLAS
HIGH

odh-dashboard: unvalidated roleRef enables cluster-admin

CVE-2026-18950
8.8
EPSS 0.4%
Auth Bypass Code Execution Framework
rhoai/odh-mod-arch-mlflow-rhel9 690 1 ATLAS
HIGH

ODH Dashboard: SA token abuse escalates to cluster-admin

CVE-2026-18949
8.8
EPSS 0.4%
Auth Bypass Data Leakage Framework
rhoai/odh-mod-arch-mlflow-rhel9 690 2 ATLAS
HIGH

Feast: authz bypass in /materialize triggers DoS

CVE-2026-18947
8.5
EPSS 0.4%
Auth Bypass DoS Training Data API
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 3.8K 3 ATLAS
HIGH

Feast: no-auth default enables RCE via malicious UDF

CVE-2026-18941
7.7
EPSS 0.6%
Auth Bypass Code Execution DoS Framework API Training Data
rhoai/odh-pipeline-runtime-tensorflow-cuda-py312-rhel9 3.8K 4 ATLAS
HIGH

OpenShift AI Pipelines: confused deputy grants node-root

CVE-2026-18621
7.6
EPSS 0.4%
Auth Bypass Code Execution Framework API
rhaiis/vllm-cpu-rhel9 92 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