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 983 results — Medium severity, no patch
MEDIUM

Xibo CMS: missing authz on dataset CSV export leaks data

CVE-2026-50541
6.5
EPSS 0.4%
Data LeakageAuth BypassFramework
CWE-8622 ATLAS
MEDIUM

WoowBot: missing authz lets subscribers drain AI API credits

CVE-2026-111372
4.3
EPSS 0.3%
Auth BypassDoSPluginRAGAPI
wpbotCWE-8624 ATLAS
MEDIUM

VideoLLaMA2: unverified model integrity on load

CVE-2026-116608
5.4
EPSS 0.1%
Supply ChainModel PoisoningModelInferenceFramework
VideoLLaMA21.9K3 ATLAS
MEDIUM

Camel OAuth: shared token cache leaks cross-profile tokens

CVE-2026-94386
4.8
EPSS 0.3%
Data LeakageAuth BypassFrameworkAPIAgent
2 ATLAS
MEDIUM

Apache Camel CoAP: error responses leak internal details

CVE-2026-101259
5.3
EPSS 0.3%
Data LeakageData ExtractionFrameworkAPI
2 ATLAS
MEDIUM

vLLM: invalid stop_token_ids crash engine, GPU OOB write

CVE-2026-116181
6.5
EPSS 0.4%
DoSInferenceAPI
vllmCWE-129943 ATLAS
MEDIUM

vLLM: audio decompression bomb exhausts server memory

CVE-2026-116175
6.5
EPSS 0.3%
DoSInferenceAPI
vllmCWE-409943 ATLAS
MEDIUM

LangGraph CLI: deploy --verbose leaks registry token in logs

CVE-2026-115885
5.4
EPSS 0.1%
Data LeakageSupply ChainFrameworkAgent
langgraphCWE-5324.1K3 ATLAS
MEDIUM

LangGraph stores: namespace label injection crosses tenants

CVE-2026-115883
--
EPSS 0.3%
Auth BypassData LeakageFrameworkAgent
langgraphCWE-204.1K3 ATLAS
MEDIUM

Zephyr RTOS: predictable DHCPv4 xid enables gateway/DNS hijack

CVE-2026-79980
5.6
EPSS 0.2%
Social EngineeringDoSData LeakageFrameworkInference
2 ATLAS
MEDIUM

Goobi viewer: Solr injection exposes restricted records

CVE-2026-55465
5.3
EPSS 0.3%
Data LeakageAuth BypassFrameworkAPI
CWE-892 ATLAS
MEDIUM

Splunk Enterprise: CSRF via GET disables federated search

CVE-2026-76297
5.4
EPSS 0.1%
Social EngineeringDoSAPI
CWE-3522 ATLAS
MEDIUM

Red Hat CA store: weak eMudhra intermediates enable TLS MITM

CVE-2026-114406
6.8
EPSS 0.3%
Supply ChainData LeakageAuth BypassFrameworkInferenceAPI
rhoai/odh-trustyai-garak-lls-provider-dsp-rhel933 ATLAS
MEDIUM

libmodulemd: out-of-bounds read causes local DoS

CVE-2026-92824
6.2
DoSFrameworkInference
rhoai/odh-mlflow-operator-rhel96952 ATLAS
MEDIUM

libmodulemd: unbounded xmd recursion causes DoS

CVE-2026-92822
6.2
DoSFramework
rhoai/odh-mlflow-operator-rhel96951 ATLAS
MEDIUM

libmodulemd: decompression bomb causes local DoS

CVE-2026-92823
6.2
DoSFrameworkInference
rhoai/odh-mlflow-operator-rhel96951 ATLAS
MEDIUM

vLLM: cache aliasing leaks cross-request media/KV state

CVE-2026-114054
6.5
EPSS 0.3%
Data LeakageAuth BypassInferenceFramework
vllmCWE-284943 ATLAS
MEDIUMEXPLOIT AVAIL

tt-metal: path traversal in checkpoint loader

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

PeopleSoft PeopleTools: Panel Processor data tampering

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

fastllm: safetensors offset overflow enables memory corruption

CVE-2026-112107
6.3
EPSS 0.3%
Code ExecutionDoSSupply ChainInferenceModelFramework
3 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