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 1942 results — no patch
CRITICAL EXPLOIT AVAIL

h2oGPT: unauth path traversal in files API leads to RCE

CVE-2026-65700
9.8
EPSS 1.3%
Auth Bypass Code Execution API Inference
h2ogpt CWE-22 27 2 ATLAS
HIGH EXPLOIT AVAIL

CyberPanel: IDOR exposes cross-tenant backups

CVE-2026-65917
8.8
EPSS 0.4%
Auth Bypass Data Leakage DoS API
CWE-639 1 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
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
MEDIUM

PeopleSoft: unauthorized data access via Panel Processor

CVE-2026-60152
5.4
EPSS 0.2%
Auth Bypass Data Leakage Framework
MEDIUM

PeopleSoft PeopleTools: CSRF-style data tampering flaw

CVE-2026-47024
5.4
EPSS 0.2%
Auth Bypass Data Leakage Framework
HIGH EXPLOIT AVAIL

lmdeploy: SSRF via redirect bypasses private IP guard

CVE-2026-63764
8.6
EPSS 0.3%
Auth Bypass Data Leakage API Inference
lmdeploy CWE-918 1 2 ATLAS
MEDIUM

Kirby Modules: license key disclosure via activate dialog

CVE-2026-63092
4.3
EPSS 0.2%
Auth Bypass Data Leakage Plugin
CWE-862
HIGH EXPLOIT AVAIL

Kubeflow: token theft lets any user hijack accounts

CVE-2026-47237
8.0
EPSS 0.3%
Auth Bypass Data Leakage Framework API
CWE-266 3 ATLAS
HIGH

MCP Toolbox: SQLi bypasses BigQuery allowedDatasets ACL

CVE-2026-15829
--
EPSS 0.2%
Auth Bypass Data Leakage Code Execution Agent Plugin API
3 ATLAS
CRITICAL EXPLOIT AVAIL

Grav CMS API plugin: forged keys enable account takeover

CVE-2026-65007
9.6
EPSS 0.3%
Auth Bypass Plugin API
CWE-862
MEDIUM EXPLOIT AVAIL

WPBot: missing auth check lets subscribers edit RAG config

CVE-2026-14185
4.3
EPSS 0.2%
Auth Bypass Data Leakage Plugin RAG
2 ATLAS
UNKNOWN EXPLOIT AVAIL

AgenticMail: unauthenticated email hijacks AI agent

CVE-2026-57495
--
EPSS 0.3%
Prompt Injection Auth Bypass Code Execution Agent Plugin
CWE-306 5 ATLAS
MEDIUM

@ai-sdk/harness-codex: tool relay authz bypass

CVE-2026-64650
--
EPSS 0.1%
Auth Bypass Code Execution Supply Chain Agent Plugin
3 ATLAS
CRITICAL EXPLOIT AVAIL

GPT-SoVITS: unauthenticated RCE via webui.py

CVE-2026-63766
9.8
EPSS 1.7%
Code Execution Inference Framework
CWE-78 2 ATLAS
CRITICAL

ktransformers: unauth pickle RCE via ZMQ socket

CVE-2026-63767
9.8
EPSS 0.7%
Code Execution Auth Bypass Inference Framework
ktransformers 9.0K 3 ATLAS
MEDIUM

onenote_parser: path traversal via crafted .onetoc2 file

CVE-2026-46671
4.4
EPSS 0.1%
DoS Data Leakage Plugin
CWE-22 2 ATLAS
UNKNOWN EXPLOIT AVAIL

Lollms: stored XSS in prompt-share DM inbox

CVE-2026-12228
--
EPSS 0.3%
Code Execution Data Leakage Framework
parisneo/lollms 2 ATLAS
HIGH

dd-trace: unbounded W3C baggage parsing enables DoS

CVE-2026-50272
7.5
EPSS 0.4%
DoS API
CWE-770 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