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 1321 results — High severity
HIGH

OpenClaw: path traversal enables arbitrary file write

CVE-2026-32055
7.6
EPSS 0.3%
Code Execution Auth Bypass Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: auth bypass lets operators invoke owner control-plane

CVE-2026-32051
8.8
EPSS 0.4%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 5 ATLAS 2 incidents
HIGH

OpenClaw: media limit bypass enables memory exhaustion DoS

CVE-2026-32049
7.5
EPSS 0.5%
DoS Agent
OpenClaw 4 3 ATLAS
HIGH

OpenClaw: sandbox escape via cross-agent spawn bypass

CVE-2026-32048
7.5
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: privilege escalation via unpaired device identity

CVE-2026-32042
8.8
EPSS 0.4%
Auth Bypass Data Extraction Agent API
OpenClaw 4 5 ATLAS 1 incident
HIGH

Feast: unauth path traversal leaks any file

CVE-2026-23536
7.5
EPSS 0.6%
Data Extraction Auth Bypass RAG Inference Framework
rhoai/odh-workbench-jupyter-datascience-cpu-py312-rhel9 1.9K 3 ATLAS
HIGH

langflow: IDOR enables unauthorized data access

CVE-2026-33053
8.8
EPSS 0.4%
Supply Chain Code Execution DoS Framework Agent API
langflow CWE-639 5 ATLAS
HIGH

OpenClaw: auth bypass enables high-privilege agent control

CVE-2026-32034
8.1
EPSS 0.4%
Auth Bypass Code Execution Agent API
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: SHELL env var injection enables local RCE

CVE-2026-32032
7.8
EPSS 0.1%
Code Execution Agent
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: path traversal exposes host files via SCP

CVE-2026-32030
7.5
EPSS 0.3%
Data Extraction Data Leakage Agent
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: WebSocket auth bypass enables agent hijack

CVE-2026-32025
7.5
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 5 ATLAS 1 incident
HIGH

OpenClaw: approval gating bypass enables shell execution

CVE-2026-32023
7.1
EPSS 0.3%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: SSRF bypass via incomplete IPv4 range validation

CVE-2026-32019
7.4
EPSS 0.2%
Auth Bypass Data Extraction Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: allowlist bypass enables arbitrary file write

CVE-2026-32017
7.1
EPSS 0.3%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: path bypass allows unauthorized binary execution

CVE-2026-32016
7.8
EPSS 0.1%
Code Execution Auth Bypass Agent
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: PATH hijack bypasses exec allowlist controls

CVE-2026-32015
7.8
EPSS 0.1%
Code Execution Auth Bypass Supply Chain Agent Plugin Framework
OpenClaw 4 5 ATLAS 1 incident
HIGH

OpenClaw: metadata spoofing bypasses agent command policies

CVE-2026-32014
8.0
EPSS 0.2%
Auth Bypass Code Execution Agent Framework
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: symlink traversal enables host file read/write

CVE-2026-32013
8.8
EPSS 0.6%
Code Execution Data Extraction Auth Bypass Agent Plugin Framework
OpenClaw 4 5 ATLAS 1 incident
HIGH

OpenClaw: pre-auth webhook DoS exhausts parser resources

CVE-2026-32011
7.5
EPSS 0.4%
DoS Agent
OpenClaw 4 3 ATLAS
HIGH EXPLOIT AVAIL

libarchive: RAR heap OOB read leaks memory in vLLM stacks

CVE-2026-4424
7.5
EPSS 0.9%
Data Extraction Supply Chain Inference
rhaiis/vllm-cuda-rhel9 130 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