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 472 results — Medium severity, Active exploitation
MEDIUM EXPLOIT AVAIL

open-webui: blind SSRF via image-edit URL fetch

CVE-2026-34225
4.3
EPSS 0.3%
Privacy Violation API Plugin
open-webui CWE-918 3 2 ATLAS
MEDIUM EXPLOIT AVAIL

onnx: crafted model triggers SIGSEGV in version_converter

CVE-2026-44512
5.5
EPSS 0.2%
DoS Supply Chain Model Framework
onnx Patch: 1.22.0 CWE-476 1.1K 3 ATLAS
MEDIUM EXPLOIT AVAIL

Coder: CORS bypass via workspace subdomain proxy

CVE-2026-55438
5.8
EPSS 0.2%
Auth Bypass Data Leakage Training Data API
github.com/coder/coder/v2 Patch: 2.34.2 CWE-346 6.1K 2 ATLAS
MEDIUM EXPLOIT AVAIL

vLLM: audio upload OOMs process before size check

CVE-2026-55646
6.5
EPSS 0.5%
DoS Inference API
vllm Patch: 0.24.0 CWE-400 92 2 ATLAS
MEDIUM EXPLOIT AVAIL

ONNX: OOB read in shape inference parsing untrusted models

CVE-2026-14647
4.3
EPSS 0.4%
Code Execution DoS Model Framework
onnx CWE-119 1.1K 2 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: IDOR cross-tenant data pollution

CVE-2026-58653
4.3
EPSS 0.3%
Auth Bypass Agent API
praisonai 1 2 ATLAS
MEDIUM EXPLOIT AVAIL

Keras: incomplete fix reopens HDF5 arbitrary file read

CVE-2026-12480
5.5
EPSS 0.2%
Data Leakage Supply Chain Privacy Violation Model Training Data
keras Patch: 3.12.3 CWE-73 1.5K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Open WebUI: SSRF in web retrieval hits internal services

CVE-2026-56399
5.0
EPSS 0.5%
Auth Bypass Code Execution Data Leakage RAG API
open-webui 3 3 ATLAS
MEDIUM EXPLOIT AVAIL

Pinpoint: insecure JWT cookie enables session hijacking

CVE-2026-57948
6.8
EPSS 0.2%
Auth Bypass Data Leakage Inference
pinpoint 2 ATLAS
MEDIUM EXPLOIT AVAIL

Edimax router: OS command injection via web form

CVE-2026-13581
6.3
EPSS 2.0%
Code Execution Framework
MEDIUM EXPLOIT AVAIL

Edimax EW-7478APC: unauth OS command injection

CVE-2026-13561
6.3
EPSS 2.0%
Code Execution
2 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: NODE_OPTIONS denylist bypass allows RCE

CVE-2026-58057
5.0
EPSS 1.6%
Code Execution Agent Plugin
flowise CWE-178 3 ATLAS
MEDIUM EXPLOIT AVAIL

Mattermost: OpenAI API key leaks into logs on auth errors

CVE-2026-9699
6.8
EPSS 0.5%
Data Leakage Plugin API
3 ATLAS
MEDIUM EXPLOIT AVAIL

wolfSSL: TLS session resumption skips SNI/ALPN check

CVE-2026-11703
--
EPSS 0.4%
Auth Bypass API Inference
1 ATLAS
MEDIUM EXPLOIT AVAIL

LibreChat: SSRF via custom API baseURL exposes internal network

CVE-2026-54033
6.5
EPSS 0.4%
Data Extraction Data Leakage API Agent
CWE-918 5 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: SQL injection exposes AI credential store

CVE-2025-71332
6.5
EPSS 0.5%
Data Extraction Code Execution Agent Framework
Flowise CWE-89 4 ATLAS
MEDIUM EXPLOIT AVAIL

Gogs: XSS via data URI in ipynb sanitizer endpoint

CVE-2026-52816
--
EPSS 0.7%
Code Execution Data Leakage Auth Bypass API
gogs.io/gogs Patch: 0.14.3 CWE-79 1.9K 5 ATLAS
MEDIUM EXPLOIT AVAIL

Keras: path traversal via layer names allows arbitrary file write

CVE-2026-12479
6.1
EPSS 0.4%
Supply Chain Code Execution Framework Model
keras Patch: 3.12.3 CWE-22 1.5K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Langflow: code injection via Bundle URL Loader (PoC)

CVE-2026-12822
5.3
EPSS 0.3%
Code Execution Data Extraction Framework Agent
langflow CWE-74 4 ATLAS
MEDIUM EXPLOIT AVAIL

Flowise: path traversal in S3 loader exposes documents

CVE-2026-12821
6.3
EPSS 0.5%
Data Extraction Data Leakage Agent RAG Framework
Flowise CWE-22 5 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