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 481 results — Critical severity
CRITICAL EXPLOIT AVAIL

Flowise: unauth OAuth refresh endpoint leaks access tokens

CVE-2026-70478
--
EPSS 0.5%
Auth Bypass Data Leakage Agent Plugin
flowise Patch: 3.1.3 CWE-200 4 ATLAS
CRITICAL

Flowise: RCE via pickle deserialization in CSVAgent

CVE-2026-69256
--
EPSS 0.8%
Code Execution Supply Chain Agent Framework
flowise Patch: 3.1.3 CWE-94 3 ATLAS
CRITICAL

Flowise: code injection in agent tools escapes vm2 sandbox

CVE-2026-69253
--
EPSS 0.6%
Code Execution Agent Plugin
flowise-components Patch: 3.1.3 CWE-95 3 ATLAS
CRITICAL EXPLOIT AVAIL

SiYuan: SQL injection in searchDocs allows DB tampering

CVE-2026-69085
10.0
EPSS 0.9%
Data Extraction Auth Bypass Privacy Violation RAG API
3 ATLAS
CRITICAL EXPLOIT AVAIL SCANNER

SiYuan: SQL injection in search endpoint exposes notebooks

CVE-2026-69084
10.0
EPSS 1.1%
Data Extraction Auth Bypass Data Leakage API Plugin
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260721002947-23a17d44b5f3 CWE-89 3.1K 2 ATLAS
CRITICAL EXPLOIT AVAIL

SiYuan: unauthenticated SQLi in full-text search endpoint

CVE-2026-69083
10.0
EPSS 0.4%
Code Execution Data Leakage RAG
github.com/siyuan-note/siyuan/kernel Patch: 0.0.0-20260721004815-cf42dd5680c8 3.1K 2 ATLAS
CRITICAL

ComfyUI: unauthenticated RCE via pickle upload

CVE-2026-68771
9.8
EPSS 0.8%
Code Execution Supply Chain Training Data Framework
CWE-502 4 ATLAS
CRITICAL EXPLOIT AVAIL

sentence-transformers: trust gate bypass enables RCE

CVE-2026-68770
9.8
EPSS 0.6%
Auth Bypass Code Execution Supply Chain Model Inference Framework
sentence-transformers CWE-94 3.0K 4 ATLAS
CRITICAL

Pterodactyl Wings: egg template leaks daemon secrets

CVE-2026-52855
9.9
EPSS 0.3%
Data Leakage Auth Bypass Plugin
github.com/pterodactyl/wings Patch: 1.12.3 CWE-200 505 1 ATLAS
CRITICAL EXPLOIT AVAIL

OpenClaw Dashboard: stored XSS enables admin takeover

CVE-2026-66421
9.3
EPSS 0.5%
Code Execution Auth Bypass Data Leakage Agent Framework
openclaw-dashboard CWE-79 3 3 ATLAS
CRITICAL EXPLOIT AVAIL

OpenClaw: stored XSS via login field hijacks admin

CVE-2026-66418
9.3
EPSS 0.5%
Code Execution Auth Bypass Agent Framework
openclaw CWE-79 3 3 ATLAS
CRITICAL EXPLOIT AVAIL

amplify-codegen-ui: eval injection enables build-time RCE

CVE-2025-4318
--
EPSS 0.9%
Code Execution Supply Chain Framework
@aws-amplify/codegen-ui-react Patch: 2.20.3 CWE-95 635 2 ATLAS
CRITICAL

Langflow: unsanitized code input enables RCE

CVE-2026-12946
9.9
EPSS 0.4%
Code Execution Auth Bypass Framework Agent
langflow 2 ATLAS
CRITICAL EXPLOIT AVAIL

SGLang: RCE via unsafe pickle deserialization on weight load

CVE-2026-15976
9.8
EPSS 0.5%
Code Execution Supply Chain Inference Model Framework
4 ATLAS
CRITICAL

Langflow: unauth RCE via MCP env var injection

CVE-2026-12940
9.8
EPSS 0.7%
Code Execution Framework Agent Plugin
langflow CWE-78 4 ATLAS
CRITICAL

Langflow: PythonREPL sandbox escape enables RCE

CVE-2026-13435
9.9
EPSS 0.3%
Code Execution Framework Agent Plugin
Langflow OSS CWE-94 4 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
CRITICAL

Plesk XML-RPC: blind SQLi exposes full panel DB

CVE-2026-58046
9.9
EPSS 0.4%
Data Extraction Privacy Violation API
CRITICAL

Budibase: unauth SSRF leaks stored REST API credentials

GHSA-mqhr-6j6h-74p5
--
Auth Bypass Data Leakage API Framework
@budibase/server CWE-200 635 3 ATLAS
CRITICAL EXPLOIT AVAIL

h2oGPT: unauth path traversal in files API leads to RCE

CVE-2026-65700
9.8
EPSS 1.5%
Auth Bypass Code Execution API Inference
h2ogpt CWE-22 27 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