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
HIGH

Langflow: path traversal exposes arbitrary server files

CVE-2026-12942
7.5
EPSS 0.4%
Data Leakage Data Extraction Framework Agent
Langflow OSS CWE-22 3 ATLAS
CRITICAL EXPLOIT AVAIL

flyto-core: arbitrary file write via bypassed path guard

CVE-2026-67429
10.0
EPSS 0.5%
Code Execution Auth Bypass Agent Plugin
CWE-22 4 ATLAS
HIGH

FTC E-Commerce Panel: authentication bypass

CVE-2026-12722
8.2
EPSS 0.3%
Auth Bypass Data Leakage Framework
CWE-306 1 ATLAS
CRITICAL

Plesk XML-RPC: blind SQLi exposes full panel DB

CVE-2026-58046
9.9
EPSS 0.3%
Data Extraction Privacy Violation API
HIGH

pgvector: integer wraparound in index build enables RCE

CVE-2026-18022
8.8
EPSS 0.3%
Code Execution DoS RAG
pgvector 323 2 ATLAS
HIGH

Langflow: FAISS namespace reuse leaks cross-user vectors

CVE-2026-13442
7.1
EPSS 0.2%
Data Leakage Privacy Violation Auth Bypass RAG Framework
langflow CWE-520 4 ATLAS
MEDIUM

WPBot: unauth PII exfil via chat transcript flaw

CVE-2026-16773
5.3
EPSS 0.3%
Data Leakage Privacy Violation Plugin Agent
WPBot – AI ChatBot for Live Support, Lead Generation, AI Services CWE-200 3 ATLAS
MEDIUM

WPBot: unauthenticated email abuse via wp_mail()

CVE-2026-16774
5.3
EPSS 0.2%
Auth Bypass Social Engineering Plugin
WPBot – AI ChatBot for Live Support, Lead Generation, AI Services 2 ATLAS
LOW EXPLOIT AVAIL

WPBot: admin-set field IDs enable stored SQLi

CVE-2026-14189
3.8
EPSS 0.2%
Data Leakage Code Execution Plugin Agent
wpbot 1 ATLAS
MEDIUM EXPLOIT AVAIL

openclaw-cn: unpatched SSRF in browser agent click API

CVE-2026-17458
6.3
EPSS 0.2%
Data Extraction Auth Bypass Agent API
CWE-918 3 ATLAS
MEDIUM EXPLOIT AVAIL

openclaw-cn: scheme handler bypass exposes data

CVE-2026-17457
4.3
EPSS 0.3%
Data Leakage Auth Bypass Agent
CWE-200 2 ATLAS
HIGH

Bedrock AgentCore: argument injection sandbox RCE

CVE-2026-16796
7.3
EPSS 0.3%
Code Execution Agent Framework
CWE-88 2 ATLAS
HIGH

Budibase: SSRF guard bypass via DNS rebinding

GHSA-v42f-v8xc-j435
8.5
Data Extraction Auth Bypass Privacy Violation Framework Agent Plugin
@budibase/server CWE-367 16 2 ATLAS
HIGH

Budibase: CSRF hijacks AI chat-agent identity binding

GHSA-pvcr-8mvp-w8qr
7.7
Auth Bypass Social Engineering Data Leakage Agent API
CWE-285 3 ATLAS
CRITICAL

Budibase: unauth SSRF leaks stored REST API credentials

GHSA-mqhr-6j6h-74p5
--
Auth Bypass Data Leakage API Framework
@budibase/server CWE-200 619 3 ATLAS
MEDIUM EXPLOIT AVAIL

datasets: path traversal via file_name leaks local files

CVE-2026-66007
6.5
EPSS 0.5%
Data Leakage Supply Chain Training Data Framework
datasets CWE-22 2.9K 4 ATLAS
MEDIUM EXPLOIT AVAIL

Jan: CORS misconfig exposes local LLM API to network

CVE-2026-66005
6.3
EPSS 0.2%
Auth Bypass Data Leakage Code Execution API Agent Plugin
CWE-183 4 ATLAS
MEDIUM

Zephyr RTOS: ext2 mount DoS via crafted superblock

CVE-2026-7007
4.6
EPSS 0.2%
DoS Inference
1 ATLAS
MEDIUM EXPLOIT AVAIL

Datasets: symlink following enables arbitrary file write

CVE-2026-65010
6.6
EPSS 0.1%
Code Execution Supply Chain Training Data Framework
datasets CWE-61 2.9K 1 ATLAS
MEDIUM EXPLOIT AVAIL

Diffusers: path traversal via weight_map exposes files

CVE-2026-65920
4.3
EPSS 0.3%
Data Leakage Supply Chain Model Framework
diffusers 427 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