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
3,023

AI/ML CVEs Tracked

424

Critical

115

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 3023 results
CRITICAL EXPLOIT AVAIL

onnx: Integrity Verification bypass enables tampering

CVE-2026-28500
9.1
EPSS 0.3%
Supply Chain Model Poisoning Code Execution Framework RAG API
onnx CWE-345 1.1K 10 ATLAS
MEDIUM

OpenClaw: symlink race bypasses agent run approval

CVE-2026-27545
6.1
EPSS 0.1%
Auth Bypass Code Execution Agent
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: prototype pollution bypasses command gate

CVE-2026-27524
4.3
EPSS 0.2%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: sandbox path traversal bypasses bind isolation

CVE-2026-27523
6.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: path traversal enables arbitrary file read via media actions

CVE-2026-27522
6.5
EPSS 0.4%
Data Extraction Auth Bypass Agent
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: $SHELL env hijack enables arbitrary code execution

CVE-2026-22217
6.1
EPSS 0.1%
Code Execution Supply Chain Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: SSRF guard bypass exposes internal services

CVE-2026-22181
7.6
EPSS 0.2%
Auth Bypass Data Extraction Agent
OpenClaw 4 3 ATLAS 1 incident
MEDIUM

OpenClaw: path traversal enables arbitrary file writes

CVE-2026-22180
5.3
EPSS 0.1%
Code Execution Supply Chain Agent Plugin
OpenClaw 4 5 ATLAS 1 incident
HIGH EXPLOIT AVAIL

OpenClaw: allowlist bypass enables arbitrary OS command exec

CVE-2026-22179
7.2
EPSS 0.6%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 5 ATLAS 1 incident
MEDIUM

OpenClaw: ReDoS via Feishu mention metadata

CVE-2026-22178
6.5
EPSS 0.3%
DoS Agent Framework
OpenClaw 4 3 ATLAS
HIGH

OpenClaw: allowlist bypass lets agents run any command

CVE-2026-22175
7.1
EPSS 0.3%
Auth Bypass Code Execution Agent
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: local token leak via CDP probe hijack

CVE-2026-22174
6.8
EPSS 0.1%
Auth Bypass Data Leakage Agent API
OpenClaw 4 3 ATLAS
HIGH

OpenClaw: path traversal allows arbitrary file write

CVE-2026-22171
8.2
EPSS 0.3%
Code Execution Data Leakage Agent Plugin
OpenClaw 4 3 ATLAS
MEDIUM

OpenClaw: empty allowlist bypasses BlueBubbles DM auth

CVE-2026-22170
6.5
EPSS 0.3%
Auth Bypass Prompt Injection Agent Plugin
OpenClaw 4 3 ATLAS
MEDIUM

OpenClaw: safeBins allowlist bypass enables command exec

CVE-2026-22169
6.7
EPSS 0.2%
Code Execution Auth Bypass Agent Plugin
OpenClaw 4 3 ATLAS
MEDIUM

OpenClaw: cmd.exe argument smuggling evades approval log

CVE-2026-22168
6.5
EPSS 0.4%
Code Execution Auth Bypass Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
HIGH EXPLOIT AVAIL

Ray Dashboard: unauthenticated path traversal file read

CVE-2026-32981
7.5
EPSS 0.9%
Data Extraction Auth Bypass Framework Inference
ray Patch: 2.8.1 CWE-22 620 4 ATLAS
UNKNOWN

GROWI: Missing Auth allows unauthorized operations

CVE-2026-25083
--
EPSS 0.3%
Prompt Injection Data Leakage Model Poisoning API RAG Inference
CWE-862 8 ATLAS
HIGH EXPLOIT AVAIL

mlflow: Code Injection enables RCE

CVE-2025-14287
7.5
EPSS 1.5%
Supply Chain Model Poisoning Code Execution Framework Model
mlflow Patch: 3.8.0rc0 CWE-94 680 7 ATLAS
MEDIUM

fickling: Allowlist Bypass evades input filtering

GHSA-5cxw-w2xg-2m8h
--
Supply Chain Data Extraction Code Execution Framework Model Training Data
fickling Patch: 0.1.10 CWE-184 61 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