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 4307 results
HIGH

vLLM: RCE via code_revision in /tokenize endpoint

CVE-2026-114053
8.1
EPSS 0.5%
Code ExecutionSupply ChainInferenceAPIModel
vllmPatch: 0.31.0CWE-94943 ATLAS
HIGH

vLLM: unauthenticated /tokenize exhausts memory (MOSS-Audio)

CVE-2026-114052
7.5
EPSS 0.5%
DoSInferenceAPI
vllmCWE-770943 ATLAS
HIGH

vLLM: unauth DoS via min_tokens hangs generation

CVE-2026-114051
7.5
EPSS 0.4%
DoSInferenceAPI
vllmCWE-248943 ATLAS
HIGH

vLLM: forged multimodal UUID crashes inference engine

CVE-2026-114050
7.5
EPSS 0.2%
DoSInferenceFrameworkAPI
vllmPatch: 0.31.0CWE-345943 ATLAS
LOW

vLLM: stale token mask leaks across requests

CVE-2026-114049
3.7
EPSS 0.3%
Data LeakageInferenceAPI
vllmCWE-440942 ATLAS
MEDIUMEXPLOIT AVAIL

tt-metal: path traversal in checkpoint loader

CVE-2026-113743
6.3
EPSS 0.4%
Supply ChainData LeakageFrameworkModelInference
3 ATLAS
HIGH

Oracle Siebel CRM: unauthenticated data access (non-AI)

CVE-2026-91445
8.2
EPSS 0.2%
Auth BypassData LeakageFramework
MEDIUM

PeopleSoft PeopleTools: Panel Processor data tampering

CVE-2026-87355
4.4
EPSS 0.2%
Data LeakageFramework
HIGHEXPLOIT AVAIL

Issuu Panel WP plugin: file inclusion enables RCE

CVE-2016-20101
8.1
EPSS 0.4%
Code ExecutionPlugin
CWE-982 ATLAS
MEDIUMEXPLOIT AVAIL

Pillow: TIFF tile heap over-read enables DoS and memory leak

CVE-2026-112395
6.5
EPSS 0.5%
DoSData LeakageFrameworkInference
pillowPatch: 13.0.0CWE-1226.3K3 ATLAS
CRITICALEXPLOIT AVAIL

Pillow: heap overflow via lossless JPEG in thumbnail()

CVE-2026-112403
--
EPSS 0.9%
DoSCode ExecutionSupply ChainFrameworkInferenceTraining Data
PillowPatch: 13.0.0CWE-1226.3K3 ATLAS
HIGHEXPLOIT AVAIL

DrayTek Vigor2960: path traversal in Apmupload

CVE-2026-113392
7.4
EPSS 0.4%
Auth BypassFramework
CWE-221 ATLAS
UNKNOWN

TYPO3 OpenAI plugin: API key exposed to backend users

CVE-2026-113459
--
EPSS 0.4%
Data LeakageData ExtractionPluginAPI
3 ATLAS
CRITICALEXPLOIT AVAILSCANNER

Langchain-Chatchat: unauthenticated shell tool RCE

CVE-2026-75128
9.8
EPSS 2.2%
Code ExecutionAuth BypassFrameworkAgentPlugin
CWE-3064 ATLAS
HIGH

Pingora: HTTP/2 header flood allows remote DoS

CVE-2026-105297
7.5
EPSS 0.4%
DoSAPIInference
2 ATLAS
HIGH

Langflow: missing ownership checks enable message tampering

CVE-2026-107366
8.3
EPSS 0.3%
Auth BypassPrompt InjectionData LeakageFrameworkAgent
langflowCWE-6395 ATLAS
HIGHEXPLOIT AVAIL

MLflow: path traversal allows arbitrary file write

CVE-2026-53995
8.2
EPSS 0.6%
Auth BypassSupply ChainFrameworkAPI
mlflowPatch: 3.17.2CWE-226952 ATLAS
MEDIUM

Mercury: stored XSS via unsanitized Markdown HTML

CVE-2026-111059
6.1
EPSS 0.3%
Code ExecutionData LeakageFramework
mercuryPatch: 3.2.11CWE-793.0K2 ATLAS
HIGH

CrewAI Tools: SSRF in SeleniumScrapingTool leaks cloud creds

CVE-2026-112308
7.4
EPSS 0.2%
Prompt InjectionData ExtractionData LeakageAgentPluginFramework
crewaiCWE-9183715 ATLAS
CRITICAL

Mercury: missing auth allows anonymous kernel RCE

CVE-2026-111058
9.8
EPSS 0.5%
Auth BypassCode ExecutionFramework
mercuryPatch: 3.2.6CWE-8623.0K4 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