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
2,404

AI/ML CVEs Tracked

347

Critical

310

New This Week

18

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 1577 results — no patch
MEDIUM

OpenClaw: TOCTOU race condition enables sandbox file escape

CVE-2026-32977
6.3
EPSS 0.1%
Code Execution Auth Bypass Agent Framework
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: auth bypass mutates protected agent config

CVE-2026-32976
6.5
EPSS 0.2%
Auth Bypass Agent
OpenClaw 4 3 ATLAS 1 incident
HIGH

OpenClaw: approval UI spoofing enables local RCE

CVE-2026-32971
7.1
EPSS 0.3%
Code Execution Auth Bypass Social Engineering Agent
OpenClaw 4 5 ATLAS 1 incident
LOW

OpenClaw: credential fallback bypasses local auth boundary

CVE-2026-32970
2.5
EPSS 0.1%
Auth Bypass Data Extraction Agent
OpenClaw 4 4 ATLAS 1 incident
MEDIUM

OpenClaw: script approval bypass allows code execution

CVE-2026-32921
6.3
EPSS 0.2%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 5 ATLAS 2 incidents
HIGH

OpenClaw: workspace plugin auto-load enables RCE

CVE-2026-32920
8.4
EPSS 0.3%
Supply Chain Code Execution Agent Plugin
OpenClaw 4 6 ATLAS 1 incident
CRITICAL

OpenClaw: RCE via unsanitized iMessage SCP paths

CVE-2026-32917
9.8
EPSS 2.0%
Code Execution Agent
OpenClaw 4 3 ATLAS 1 incident
CRITICAL

OpenClaw: auth bypass enables unauth agent execution

CVE-2026-32916
9.4
EPSS 0.5%
Auth Bypass Code Execution Agent Plugin
OpenClaw 4 5 ATLAS 1 incident
HIGH

1millionbot Millie: Boolean prompt injection bypasses restrictions

CVE-2026-4399
7.5
EPSS 0.3%
Prompt Injection Jailbreak API Agent
6 ATLAS 3 incidents
HIGH

gdk-pixbuf: JPEG heap overflow crashes vLLM inference

CVE-2026-5201
7.5
EPSS 1.1%
DoS Inference
rhaiis/vllm-cuda-rhel9 130 2 ATLAS
CRITICAL

telnyx: PyPI supply chain attack steals cloud creds

GHSA-955r-262c-33jc
--
Supply Chain Code Execution Data Extraction Framework API Agent
CWE-506 7 ATLAS 2 incidents
HIGH EXPLOIT AVAIL

awesome-llm-apps MCP Agent: cross-session credential theft

CVE-2026-29872
8.2
EPSS 0.3%
Data Leakage Auth Bypass Privacy Violation Agent API Plugin
7 ATLAS
CRITICAL

CrewAI: Docker sandbox fallback enables RCE

CVE-2026-2287
9.8
EPSS 0.7%
Code Execution Auth Bypass Supply Chain Agent Framework Plugin
5 ATLAS 1 incident
CRITICAL

CrewAI: SSRF via unvalidated RAG tool URLs exposes internal services

CVE-2026-2286
9.8
EPSS 0.5%
Data Extraction Auth Bypass Privacy Violation Agent RAG Framework
5 ATLAS
HIGH

CrewAI: arbitrary file read via JSON loader tool

CVE-2026-2285
7.5
EPSS 0.6%
Data Extraction Data Leakage Prompt Injection Framework Agent Plugin
6 ATLAS
CRITICAL EXPLOIT AVAIL

CrewAI: RCE via Docker fallback in CodeInterpreter

CVE-2026-2275
9.6
EPSS 0.4%
Code Execution Auth Bypass Agent Framework Plugin
6 ATLAS 1 incident
HIGH

libarchive: integer overflow in zisofs hits vllm containers

CVE-2026-5121
7.5
EPSS 1.1%
Code Execution Data Extraction Inference
rhaiis/vllm-cuda-rhel9 130 3 ATLAS
HIGH

OpenClaw: gateway credential exposed in pairing setup codes

CVE-2026-33575
7.5
EPSS 0.2%
Auth Bypass Data Leakage Agent API
OpenClaw 4 5 ATLAS 1 incident
MEDIUM

OpenClaw: TOCTOU path traversal enables arbitrary file write

CVE-2026-33574
6.2
EPSS 0.1%
Supply Chain Code Execution Agent Plugin
OpenClaw 4 4 ATLAS 1 incident
HIGH

OpenClaw: workspace boundary bypass, arbitrary exec

CVE-2026-33573
8.8
EPSS 0.3%
Auth Bypass Code Execution Data Extraction Agent Framework
OpenClaw 4 7 ATLAS 1 incident

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