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
4,307

AI/ML CVEs Tracked

533

Critical

95

New This Week

25

In CISA KEV

Sort:DateCVSSEPSSKEV firstMost exploited
Filter:AllCriticalHighMediumKEV onlyActive exploitationHas patchNo patch

Latest AI Security Threats

Showing 20 of 1908 results — High severity
HIGH

flash-attention: RCE via unsafe checkpoint deserialization

CVE-2026-31253
7.3
EPSS 0.2%
Code ExecutionSupply ChainFrameworkTraining Data
flash_attnCWE-9426.1K4 ATLAS
HIGHEXPLOIT AVAIL

BentoML: Dockerfile injection enables build-time RCE

CVE-2026-44346
8.8
EPSS 0.3%
Supply ChainCode ExecutionFrameworkInference
bentomlPatch: 1.4.39CWE-78235 ATLAS
HIGHEXPLOIT AVAIL

BentoML: unsanitized base_image allows Dockerfile RCE

CVE-2026-44345
8.8
EPSS 0.3%
Supply ChainCode ExecutionFramework
bentomlPatch: 1.4.39CWE-78234 ATLAS
HIGHEXPLOIT AVAIL

open-webui: IDOR exposes cross-user AI memory data

CVE-2026-44570
8.3
EPSS 0.3%
Auth BypassData ExtractionPrivacy ViolationAPIAgent
open-webuiPatch: 0.6.19CWE-63925 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: IDOR enables cross-user message tampering

CVE-2026-44569
7.1
EPSS 0.3%
Auth BypassAPIFramework
open-webuiPatch: 0.6.19CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

open-webui: path traversal enables file write/delete

CVE-2026-44565
8.1
EPSS 0.5%
Code ExecutionDoSInferenceFramework
open-webuiPatch: 0.6.10CWE-2225 ATLAS
HIGH

open-webui: CORS misconfiguration enables 1-click RCE

GHSA-6xcp-7mpr-m7wm
8.3
Code ExecutionAuth BypassFrameworkInference
open-webuiPatch: 0.3.33CWE-61325 ATLAS1 incident
HIGH

PraisonAI: tar symlink bypass allows arbitrary file write

CVE-2026-44340
7.5
EPSS 0.4%
Supply ChainCode ExecutionAgentFramework
PraisonAIPatch: 4.6.37CWE-2215 ATLAS1 incident
HIGHEXPLOIT AVAIL

praisonaiagents: tool bypass enables undeclared callable exec

CVE-2026-44339
8.6
EPSS 0.4%
Code ExecutionAuth BypassAgentFramework
PraisonAIPatch: 4.6.37CWE-47015 ATLAS1 incident
HIGHEXPLOIT AVAILSCANNER

PraisonAI: unauthenticated API triggers agent workflows

CVE-2026-44338
7.3
EPSS 32.6%
Auth BypassCode ExecutionDoSAgentFramework
PraisonAIPatch: 4.6.34CWE-30617 ATLAS
HIGH

LangChain: deserialization poisons LLM chat history

CVE-2026-44843
8.2
EPSS 0.4%
Prompt InjectionCode ExecutionSupply ChainFrameworkAgent
langchain-corePatch: 1.3.3CWE-5026.3K5 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: path traversal + file upload leads to RCE

CVE-2026-44566
7.3
EPSS 0.3%
Code ExecutionSupply ChainInferenceModel
open-webuiPatch: 0.1.124CWE-2225 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: auth bypass gives pending users full LLM access

CVE-2026-44567
7.3
EPSS 0.2%
Auth BypassData ExtractionDoSAPIInference
open-webuiPatch: 0.1.124CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

open-webui: XSS via XLSX preview enables session hijack

CVE-2026-44549
7.3
EPSS 0.3%
Code ExecutionData ExtractionAuth BypassFrameworkAPI
open-webuiPatch: 0.8.0CWE-7927 ATLAS
HIGH

open-webui: RAG poisoning via unauthorized KB overwrite

CVE-2026-44554
8.1
EPSS 0.3%
Auth BypassModel PoisoningPrompt InjectionRAGAPIFramework
open-webuiPatch: 0.9.0CWE-86228 ATLAS
HIGH

open-webui: auth bypass allows unrestricted model access

CVE-2026-44556
7.1
EPSS 0.3%
Auth BypassDoSData ExtractionAPIInferenceModel
open-webuiPatch: 0.9.0CWE-28428 ATLAS
HIGHEXPLOIT AVAIL

open-webui: access control bypass via model chaining

CVE-2026-44555
7.6
EPSS 0.3%
Auth BypassAPIModelInference
open-webuiPatch: 0.9.0CWE-86224 ATLAS
HIGH

open-webui: Redis cache poisoning enables cross-instance tool hijack

CVE-2026-44552
8.7
EPSS 0.3%
Supply ChainData ExtractionPrompt InjectionAgentPluginFramework
open-webuiPatch: 0.9.0CWE-66826 ATLAS
HIGH

open-webui: stale Socket.IO role allows cross-user note R/W

CVE-2026-44553
8.1
EPSS 0.3%
Auth BypassData ExtractionPrivacy ViolationAPIFramework
open-webuiPatch: 0.9.0CWE-38425 ATLAS
HIGHEXPLOIT AVAIL

open-webui: XSS in model descriptions steals session tokens

CVE-2026-44721
7.3
EPSS 0.3%
Auth BypassCode ExecutionData ExtractionAPIFramework
open-webuiPatch: 0.9.0CWE-7925 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