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
3,591

AI/ML CVEs Tracked

481

Critical

84

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 2346 results — no patch
HIGH

h2o: QPACK alloca overflow crashes HTTP/3 server

CVE-2026-55213
7.5
EPSS 0.5%
DoS Inference
CWE-789 2 ATLAS
CRITICAL EXPLOIT AVAIL

mcp-server-kubernetes: arg injection exfils bearer token

CVE-2026-61459
9.8
EPSS 2.1%
Auth Bypass Data Leakage Agent Plugin
mcp-server-kubernetes CWE-88 1 4 ATLAS
MEDIUM

Grafana: stored XSS via malicious TableNG field name

CVE-2026-8595
5.4
EPSS 0.2%
Code Execution Privacy Violation Auth Bypass Inference Plugin
2 ATLAS
CRITICAL EXPLOIT AVAIL

PraisonAI: code injection via f-string in deploy API

CVE-2026-61444
9.1
EPSS 0.6%
Code Execution Agent Framework API
praisonai CWE-94 1 3 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: IDOR lets members delete owner dependencies

CVE-2026-61441
6.5
EPSS 0.4%
Auth Bypass Agent Framework
CWE-862 1 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: unsafe dynamic import enables RCE

CVE-2026-61437
7.8
EPSS 0.2%
Supply Chain Code Execution Agent Framework
praisonaiagents CWE-693 20 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: allowlist bypass enables RCE via find -exec

CVE-2026-61434
8.8
EPSS 0.9%
Code Execution Auth Bypass Agent Framework
praisonai CWE-78 1 4 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: FastContext path traversal leaks host files

CVE-2026-61432
5.7
EPSS 0.4%
Data Extraction Data Leakage Prompt Injection Agent Plugin Framework
praisonaiagents CWE-22 20 4 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: path traversal leaks arbitrary files

CVE-2026-61431
5.5
EPSS 0.4%
Data Leakage Supply Chain Agent Framework
praisonai CWE-22 1 4 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: SSRF via webhook_url DNS rebinding

CVE-2026-60091
7.2
EPSS 0.3%
Data Leakage Auth Bypass Agent API
praisonai CWE-918 1 1 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: config.toml path traversal overwrites files

CVE-2026-60089
5.5
EPSS 0.2%
Supply Chain Code Execution Agent Framework
praisonaiagents CWE-22 20 3 ATLAS
MEDIUM EXPLOIT AVAIL

PraisonAI: injection filter bypass at HIGH threat level

CVE-2026-60086
5.3
EPSS 0.4%
Prompt Injection Agent Framework
praisonai CWE-693 1 4 ATLAS
MEDIUM

n8n: stored XSS + phishing redirect in Form Node

CVE-2026-56354
5.4
EPSS 0.2%
Social Engineering Code Execution Agent Plugin
n8n CWE-79 1 ATLAS
MEDIUM

GitHub CLI: command execution via malicious Codespace URI

CVE-2026-59831
4.4
EPSS 0.3%
Code Execution Supply Chain Framework
CWE-829 3 ATLAS
MEDIUM EXPLOIT AVAIL

SiYuan: broken access control leaks private note data

CVE-2026-59853
6.5
EPSS 0.4%
Auth Bypass Data Leakage API
CWE-862 1 ATLAS
MEDIUM EXPLOIT AVAIL

OpenClaw Android: command injection via WebView bridge

CVE-2026-15193
5.3
EPSS 1.1%
Code Execution Agent Plugin
CWE-77 3 ATLAS
HIGH

Phantom MCP: unconfined output path enables file write

GHSA-52vm-mxx8-f227
7.7
Code Execution DoS Agent Plugin
CWE-22 4 ATLAS
MEDIUM EXPLOIT AVAIL

pyload-ng: IPv6 SSRF bypass evades internal-IP guard

CVE-2026-48737
4.9
EPSS 0.2%
Auth Bypass Data Leakage Agent Plugin
pyload-ng CWE-918 488 2 ATLAS
MEDIUM

Easy Invoice (WP): missing authz on quote accept/decline

CVE-2026-9021
5.3
EPSS 0.5%
Auth Bypass Plugin
HIGH EXPLOIT AVAIL

Cline: missing Origin check on Hub enables RCE

CVE-2026-59723
8.8
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
cline CWE-346 2 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