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
3,035

AI/ML CVEs Tracked

425

Critical

122

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 3035 results
HIGH

Ajenti: missing authz lets any user install packages

CVE-2026-35175
--
EPSS 0.3%
Auth Bypass Supply Chain Code Execution Framework Plugin
CWE-862 4 ATLAS
MEDIUM

OpenClaw: SSRF in marketplace fetch hits internal AI infra

GHSA-9q7v-8mr7-g23p
--
Supply Chain Data Extraction Auth Bypass Plugin Inference Agent
openclaw Patch: 2026.3.31 CWE-918 4 4 ATLAS
HIGH

vLLM: audio downmix mismatch enables adversarial input

CVE-2026-34760
7.1
EPSS 0.3%
Adversarial Examples Supply Chain Inference Framework
vllm Patch: 0.18.0 CWE-20 130 4 ATLAS
HIGH

onnx: TOCTOU symlink following enables arbitrary file write

GHSA-q56x-g2fj-4rj6
7.1
Supply Chain Code Execution Framework Model
onnx Patch: 1.21.0 CWE-22 1.1K 4 ATLAS
HIGH EXPLOIT AVAIL

praisonaiagents: SSRF leaks cloud IAM credentials

CVE-2026-34954
8.6
EPSS 0.4%
Prompt Injection Data Extraction Agent Framework
praisonaiagents Patch: 1.5.95 CWE-918 20 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: sandbox escape via shell=True blocklist bypass

CVE-2026-34955
8.8
EPSS 0.4%
Code Execution Prompt Injection Auth Bypass Agent Framework Plugin
praisonai Patch: 4.5.97 CWE-78 1 6 ATLAS 1 incident
HIGH EXPLOIT AVAIL

PraisonAI: SSRF via api_base steals cloud IAM credentials

CVE-2026-34936
7.7
EPSS 0.3%
Data Extraction Auth Bypass Supply Chain Framework API Agent
praisonai Patch: 4.5.90 CWE-918 1 5 ATLAS
HIGH EXPLOIT AVAIL

PraisonAI: OS command injection via run_python() shell escape

CVE-2026-34937
7.8
EPSS 0.5%
Code Execution Prompt Injection Auth Bypass Agent Framework Plugin
praisonaiagents Patch: 1.5.90 CWE-78 20 6 ATLAS 1 incident
CRITICAL EXPLOIT AVAIL

praisonaiagents: sandbox bypass enables full host RCE

CVE-2026-34938
10.0
EPSS 1.3%
Code Execution Prompt Injection Supply Chain Agent Framework Plugin
praisonaiagents Patch: 1.5.90 CWE-693 20 7 ATLAS
HIGH EXPLOIT AVAIL

Open WebUI: access control bypass leaks Tool Valve API keys

CVE-2026-34222
7.7
EPSS 5.3%
Auth Bypass Data Extraction Agent Plugin Framework
open-webui Patch: 0.8.11 CWE-285 4 5 ATLAS
MEDIUM EXPLOIT AVAIL

ONNX: symlink traversal reads host files via model loading

CVE-2026-34447
5.5
EPSS 0.2%
Supply Chain Data Extraction Framework Model
onnx Patch: 1.21.0 CWE-22 1.1K 5 ATLAS
MEDIUM

ONNX: hardlink path traversal leaks sensitive files

CVE-2026-34446
4.7
EPSS 0.2%
Supply Chain Data Extraction Framework Model
onnx Patch: 1.21.0 CWE-22 1.1K 4 ATLAS
HIGH

ONNX: property overwrite via crafted model file

CVE-2026-34445
8.6
EPSS 0.3%
Supply Chain DoS Code Execution Framework Model Inference
onnx Patch: 1.21.0 CWE-20 1.1K 5 ATLAS
HIGH EXPLOIT AVAIL

ONNX: symlink path traversal allows arbitrary file read

CVE-2026-27489
8.6
EPSS 0.6%
Supply Chain Data Extraction Framework Model
onnx Patch: 1.21.0 CWE-23 1.1K 5 ATLAS
MEDIUM

Anthropic SDK: TOCTOU symlink escape in async memory tool

CVE-2026-34452
--
EPSS 0.1%
Code Execution Data Extraction Auth Bypass Framework Agent API
anthropic Patch: 0.87.0 CWE-59 6.3K 5 ATLAS 17 incidents
MEDIUM

anthropic-ai/sdk: memory tool path traversal escape

CVE-2026-34451
--
EPSS 0.3%
Prompt Injection Data Extraction Code Execution Framework Agent API
@anthropic-ai/sdk Patch: 0.81.0 CWE-22 351 6 ATLAS
MEDIUM

anthropic-sdk: insecure file perms expose agent memory

CVE-2026-34450
--
EPSS 0.1%
Data Leakage Model Poisoning Data Extraction Agent Framework API
anthropic Patch: 0.87.0 CWE-276 6.3K 4 ATLAS 17 incidents
HIGH

Claude Setup: DLL search-order hijacking LPE

CVE-2026-22561
7.8
EPSS 0.2%
Code Execution Supply Chain API Framework
3 ATLAS
CRITICAL EXPLOIT AVAIL

MLflow: command injection via model_uri in mlserver mode

CVE-2026-0596
9.6
EPSS 1.3%
Code Execution Supply Chain Framework Inference
mlflow Patch: 3.9.0 CWE-78 680 4 ATLAS 1 incident
HIGH

OpenClaw: SSRF in fal provider exposes internal services

CVE-2026-34504
8.3
EPSS 0.2%
Supply Chain Data Extraction Privacy Violation Agent Plugin API
OpenClaw 4 4 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