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

96

New This Week

25

In CISA KEV

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

Latest AI Security Threats

Showing 20 of 615 results — Active exploitation, has patch
HIGHEXPLOIT AVAIL

Microsoft APM: symlink attack leaks host files in agent deps

CVE-2026-45539
7.4
EPSS 0.7%
Supply ChainData ExtractionAgentFramework
apmPatch: 0.13.0CWE-595 ATLAS
HIGHEXPLOIT AVAILSCANNER

MLflow: auth bypass exposes Job API and trace injection

CVE-2026-2652
8.6
EPSS 20.8%
Auth BypassData ExtractionCode ExecutionFrameworkTraining Data
mlflowPatch: 3.11.0CWE-3056954 ATLAS
HIGHEXPLOIT AVAIL

utcp-cli: env leak exfiltrates all agent process secrets

CVE-2026-45370
7.7
EPSS 0.2%
Code ExecutionData ExtractionData LeakageAgentFrameworkPlugin
utcp-cliPatch: 1.1.2CWE-5266.3K6 ATLAS
CRITICALEXPLOIT AVAIL

deepseek-tui: prompt injection enables zero-approval RCE

CVE-2026-45311
9.6
EPSS 0.6%
Prompt InjectionCode ExecutionData ExtractionAgentPlugin
deepseek-tuiPatch: 0.8.23CWE-947 ATLAS
HIGHEXPLOIT AVAIL

deepseek-tui: SSRF bypass leaks cloud IAM credentials

CVE-2026-45310
7.4
EPSS 0.3%
Prompt InjectionData ExtractionAuth BypassAgentPlugin
deepseek-tuiPatch: 0.8.22CWE-9185 ATLAS
HIGHEXPLOIT AVAIL

open-webui: code exec gate bypass via API endpoint

CVE-2026-45672
8.8
EPSS 0.4%
Auth BypassCode ExecutionFrameworkInference
open-webuiPatch: 0.8.12CWE-86325 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: auth bypass enables mass file deletion

CVE-2026-45671
8.0
EPSS 0.3%
Auth BypassData ExtractionDoSRAGFramework
open-webuiPatch: 0.9.0CWE-63924 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: unauth endpoint drains embedding budget/DoS

CVE-2026-45667
6.5
EPSS 0.3%
Auth BypassDoSInferenceAPI
open-webuiPatch: 0.8.0CWE-86225 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: IDOR exposes cross-user note data

CVE-2026-45666
6.5
EPSS 0.3%
Auth BypassData ExtractionPrivacy ViolationAPIFramework
open-webuiPatch: 0.8.11CWE-63924 ATLAS
HIGHEXPLOIT AVAIL

open-webui: Stored XSS enables Super Admin session hijack

CVE-2026-45665
8.1
EPSS 0.3%
Auth BypassSocial EngineeringData ExtractionAPIFramework
open-webuiPatch: 0.8.0CWE-7925 ATLAS
HIGHEXPLOIT AVAIL

open-webui: auth bypass exposes any user's private files via RAG

CVE-2026-45402
8.1
EPSS 0.3%
Auth BypassData ExtractionData LeakageRAGFrameworkAgent
open-webuiPatch: 0.9.5CWE-63925 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF redirect bypass exposes internal services

CVE-2026-45401
8.5
EPSS 0.3%
Data ExtractionAuth BypassData LeakageFrameworkRAGAgent
open-webuiPatch: 0.9.5CWE-91824 ATLAS
HIGHEXPLOIT AVAIL

open-webui: SSRF bypass via URL parser mismatch

CVE-2026-45400
8.5
EPSS 0.3%
Auth BypassData ExtractionFrameworkInference
open-webuiPatch: 0.9.5CWE-91824 ATLAS
HIGHEXPLOIT AVAIL

Open WebUI: task auth bypass enables cross-user DoS

CVE-2026-45399
7.1
EPSS 0.3%
Auth BypassDoSInferenceAPI
open-webuiPatch: 0.9.0CWE-86224 ATLAS
HIGHEXPLOIT AVAIL

open-webui: IDOR exposes private RAG knowledge bases

CVE-2026-45398
7.5
EPSS 0.3%
Auth BypassData ExtractionModel PoisoningRAGAPI
open-webuiPatch: 0.9.5CWE-63925 ATLAS
MEDIUMEXPLOIT AVAILSCANNER

Open WebUI: unauthenticated RAG config leaks AI pipeline

CVE-2026-45397
5.3
EPSS 0.8%
Auth BypassData ExtractionRAGFramework
open-webuiPatch: 0.9.5CWE-30626 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: mass assignment enables leaderboard poisoning

CVE-2026-45396
5.4
EPSS 0.3%
Auth BypassModel PoisoningPrivacy ViolationFrameworkModel
open-webuiPatch: 0.9.5CWE-91525 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: system prompt leakage via model read API

CVE-2026-45387
4.3
EPSS 0.2%
Data LeakageAuth BypassPrivacy ViolationModelAPIFramework
open-webuiPatch: 0.9.5CWE-20024 ATLAS
MEDIUMEXPLOIT AVAIL

open-webui: auth bypass lets read-only users pin messages

CVE-2026-45386
4.3
EPSS 0.3%
Auth BypassAPIAgent
open-webuiPatch: 0.9.5CWE-63923 ATLAS
MEDIUMEXPLOIT AVAIL

Open WebUI: IDOR lets members tamper with admin messages

CVE-2026-45385
4.3
EPSS 0.3%
Auth BypassPrivacy ViolationAPIFramework
open-webuiPatch: 0.9.5CWE-63923 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