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
3,019

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 859 results — High severity, no patch
HIGH

OpenClaw: auth bypass in browser act route

CVE-2026-62226
8.5
EPSS 0.2%
Auth Bypass Data Leakage Agent
openclaw CWE-918 4 3 ATLAS
HIGH

OpenClaw: authorization bypass in device pairing

CVE-2026-62223
8.8
EPSS 0.2%
Auth Bypass Code Execution Agent
openclaw CWE-863 4 3 ATLAS
HIGH

OpenClaw: untrusted plugin loading in setup-mode

CVE-2026-62222
7.8
EPSS 0.1%
Supply Chain Code Execution Auth Bypass Agent Plugin
openclaw CWE-829 4 4 ATLAS
HIGH

OpenClaw: agent hook auth bypass via blank IDs

CVE-2026-62219
7.1
EPSS 0.2%
Auth Bypass Privacy Violation Agent Framework
openclaw CWE-863 4 2 ATLAS
HIGH

OpenClaw: authorization bypass in device pairing

CVE-2026-62218
8.8
EPSS 0.2%
Auth Bypass Agent
openclaw CWE-862 4 3 ATLAS
HIGH

OpenClaw: QQBot exec approval bypass enables RCE

CVE-2026-62217
8.8
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
openclaw CWE-863 4 3 ATLAS
HIGH

OpenClaw: auth bypass forges trusted A2UI actions

CVE-2026-62215
8.0
EPSS 0.2%
Auth Bypass Agent
openclaw CWE-345 4 3 ATLAS
HIGH

OpenClaw: TOCTOU race bypasses Teams SSRF guard

CVE-2026-62212
7.1
EPSS 0.2%
Auth Bypass Agent Plugin
openclaw CWE-367 4 2 ATLAS
HIGH

OpenClaw: agent dispatch bypasses toolsAllow authz

CVE-2026-62209
8.1
EPSS 0.2%
Auth Bypass Agent Plugin
openclaw CWE-863 4 3 ATLAS
HIGH

OpenClaw: auth bypass exposes admin agent tools

CVE-2026-62207
8.8
EPSS 0.3%
Auth Bypass Code Execution Agent Plugin
openclaw CWE-862 4 3 ATLAS
HIGH

OpenClaw: missing authorization in Discord moderation

CVE-2026-62206
7.1
EPSS 0.2%
Auth Bypass Agent Plugin
openclaw CWE-862 4 1 ATLAS
HIGH

OpenClaw: auth bypass in MS Teams message actions

CVE-2026-62205
7.1
EPSS 0.2%
Auth Bypass Agent Plugin
openclaw CWE-862 4 2 ATLAS
HIGH

OpenClaw: env var filter gap enables priv escalation

CVE-2026-62203
8.8
EPSS 0.3%
Auth Bypass Code Execution Agent
openclaw CWE-184 4 3 ATLAS
HIGH

OpenClaw: cron isolation flaw regains denied tools

CVE-2026-62202
8.8
EPSS 0.3%
Auth Bypass Code Execution Agent Plugin
openclaw CWE-863 4 3 ATLAS
HIGH

OpenClaw: exec-server bypass allows internal SSRF

CVE-2026-62201
7.7
EPSS 0.3%
Auth Bypass Data Leakage Agent Plugin
openclaw CWE-918 4 3 ATLAS
HIGH

H2O: HTTP/2 HPACK amplification enables DoS

CVE-2026-54340
7.5
EPSS 0.3%
DoS Inference API
h2o CWE-400 27 2 ATLAS
HIGH

h2o: alloca stack overflow crashes server on request

CVE-2026-44453
7.5
EPSS 0.3%
DoS Inference
CWE-770 2 ATLAS
HIGH

Quicly: QUIC DoS via oversized Connection ID overflow

CVE-2026-44436
7.5
EPSS 0.3%
DoS Inference API
CWE-120 1 ATLAS
HIGH

H2O/Quicly: unauthenticated QUIC DoS via assertion crash

CVE-2026-44435
7.5
EPSS 0.3%
DoS API Inference
CWE-400 2 ATLAS
HIGH

Quicly/H2O: QUIC flow-control bug enables memory exhaustion DoS

CVE-2026-44433
7.5
EPSS 0.3%
DoS API
CWE-400 1 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